Compare commits

..

337 Commits

Author SHA1 Message Date
Taylor Yeonbok Lee 43de73cbd6
Let ocl FC to use tile size 1 only when the # of threads is less than the w/ minimal # of threads (#24936)
### Details:
- Fix to resolve perf issue in the platforms with small # of EUs than
128.
### Tickets:
 - *ticket-id*
2024-06-12 00:27:13 +00:00
Alexandra Sidorova 1d226d4edc
[Snippets] Added dynamic Transpose support (#24733)
### Details:
- *Added dynamic Transpose support (updated related operations and
passes)*
 - *Added dynamic tests with Transpose*

### Tickets:
 - *142098*

### Prerequisites:
- https://github.com/openvinotoolkit/openvino/pull/24525
- https://github.com/openvinotoolkit/openvino/pull/24646
2024-06-11 16:45:40 +00:00
tadamczx 0908908227
[DOCS] OpenVINO Python API docs build fix (#24952)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-06-11 16:24:51 +00:00
Aleksandr Voron 4e6ee7f15e
[CPU][ARM] Enable NHWC in Reduce (#23108)
NHWC was disabled because of accuracy issue:
https://github.com/ARM-software/ComputeLibrary/issues/1044

CVS-114403

---------

Co-authored-by: eshoguli <edward.shogulin@intel.com>
2024-06-11 16:21:23 +00:00
Vladimir Paramuzov f5c3fc3330
[GPU] Model stat print, host time measurement debug knob (#24904)
### Details:
 - Added dev pass to log operations statistics when VERBOSE=1
- Added debug knob to collect network::execute() time to measure time
required to schedule all primitives
- Updated common results comparison routine to print coordinate and to
show first mismatched element info in release build
2024-06-11 15:54:33 +00:00
Jorge Ragde 8eaa65e026
[TF FE Tests] Change HSVToRGB Unit Test To Test Grayscale Image (#24935)
### Details:
- Currently, the unit test for HSVToRGB is creating a tensor of all ones
in the Grayscale special case as mentioned in
[#24875](https://github.com/openvinotoolkit/openvino/pull/24875). Since
the images are expected to be in HSV and not RGB format, this will
create images that are green, and not gray. Grayscale in HSV can be
achieved by creating a tensor with HSV entries of [0, 0, .5].

### Tickets:
 - N/A

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-06-11 14:16:48 +00:00
Andrii Staikov 91b3977169
Documentation for Transformations Python API (#24121)
### Details:

- Updating Transformations documentation
- Adding examples for Python API usage
- Adding examples for C++ API usage
- Adding patterns unit-tests

### Tickets:
 - *CVS-76333*
2024-06-11 14:07:39 +00:00
Sergey Shlyapnikov 00f4c99074
[GPU] Relax SDPA head size limitations for LLMs (#24930)
### Details:
- Relax SDPA head size limitations for LLMs from 128 only to a range of
64 to 256
- Fix accuracy issue in SDPA first token processing for
`TARGET_SEQ_LEN_BLOCK_SIZE % SUBGROUPS_PER_WG != 0` case

### Tickets:
 - *ticket-id*
2024-06-11 14:05:53 +00:00
Sebastian Golebiewski 5393b8a77a
[DOCS] Performance hint and thread scheduling update (#24946)
Fixing reference and formatting. Proofreading.
2024-06-11 10:08:07 +00:00
Edward Shogulin deb5e63ff2
[LPT] Quantization to point support (#24872)
### Details:
 - *Quaintization to point support*
 - Tests: wip

### Tickets:
 - *CVS-139557*
2024-06-11 09:11:04 +00:00
Ilya Lavrenov 395d6b7e09
Revert "More accurate shape of optimization" (#24941)
Reverts openvinotoolkit/openvino#24845

Issue CVS-143648
2024-06-11 08:43:17 +00:00
Vishniakov Nikolai 6e2286086f
[OV JS] Fix multiple Core instances (#24053)
### Details:
- New instance of Core creating on execution of readModel method. This
PR is fixing this behavior.

### Tickets:
 - 138160

---------

Co-authored-by: Alicja Miloszewska <alicja.miloszewska@intel.com>
2024-06-11 08:35:12 +00:00
Andrei Kashchikhin 1a5776e8ef
[CI] [GHA] Add `Timeout was reached` to the list of errors in rerunner (#24928)
### Tickets:
 - *142653*
2024-06-10 19:03:16 +00:00
Pawel Raasz 964c1e677b
[core] Integrate f4e2m1 with std::numeric_limits (#24929)
### Details:
 - Add custom std::numeric limits for `ov::float4_e2m1`

### Tickets:
 - [CVS-141576](https://jira.devtools.intel.com/browse/CVS-141576)
2024-06-10 19:02:29 +00:00
Andrey Babushkin ca34e4f07e
Switch ONNX model tests and TF nightly tests to a bigger runner (#24912)
### Details:

These tests require more memory
2024-06-10 12:29:59 +00:00
Maxim Vafin 4be6025fae
[PT FE] Fix segfault when prim::If can't be converted (#24914)
### Details:
- *When scripting upsample creates `prim::If` depending from input
shape, to determine which version of upsample to use: 1d, 2d or 3d. This
is not supported by openvino, but this PR fixes segfault that happen in
this case.*

### Tickets:
 - *#24270*
2024-06-10 11:35:58 +00:00
Ekaterina Aidova 73a2d13721
[PT FE]: fix gptq patching for strided tensors (#24871)
### Details:
 - *fix reshaping of strided tensor in gptq patcher*

### Tickets:
 - *CVS-140119*
 - *CVS-143119*
2024-06-10 10:50:46 +00:00
Inbasekaran Perumal 9465604223
Implement IsInf JIT Emitter for ARM64 SIMD in OpenVINO (#24471)
Hello maintainers,

I've implemented the IsInf JIT emitter for the ARM64 SIMD platform, as
outlined in the OpenVINO CPU plugin JIT emitters documentation.

This PR addresses
[#24419](https://github.com/openvinotoolkit/openvino/issues/24419).

Please let me know if any further adjustments are needed.
Thank you!
2024-06-10 10:13:46 +00:00
hyunback kim 29a4239707
[GPU] Fix to skip shape_of_subgraph when input shape is not changed. (#24795)
We only check whether shape of subgraph is changed or not in dynamic
node. But static node also need to be skipped. The node after shape_of
can be static.


### Tickets:
 - *142892*

---------

Signed-off-by: hyunback <hyunback.kim@intel.com>
2024-06-10 09:44:05 +00:00
Roman Kazantsev 5291ecc11c
[MOC] Implement LSTMCell fusion for Keras LSTM layers (#24873)
**Details:** Implement LSTMCell fusion for Keras LSTM layers. Such
sub-graph with split weights appears for bi-directional LSTM layer.
For custom model, we managed to fuse 6 LSTMCell sub-graphs and obtained
19% performance gain on CPU.

**Ticket:** 142924

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-06-10 08:28:01 +00:00
Alexandra Sidorova 3f47ab6d73
[Snippets] Add dynamic Buffer support (#24646)
### Details:
 - *Renamed `Buffer` attribute `id` to `regGroup`*
 - *Replaced `allocation_shape` of `Buffer` with `allocation_size`*
- *Added the separate pass `ComputeBufferAllocationSize` to calculate
allocation size for Buffers. By default `allocation_size` is undefined
after `InsertBuffers`*
 - *Added new attribute `cluster_id` to `Buffer`*
- *Added util expressions to LinearIR: `m_buffer_expressions` for the
quick access in configurator*
- *Added functionality to prohibit passes to update `work_amount` in
`LoopInfo`: it's needed for inner splitted loops (since their
`work_amount` is `increment` of outer splitted loop*
- *Split `SolveMemoryBuffers` logic into dynamic and static buffers: now
for all defined buffers the allocation size will be efficiently
calculated and update `offsets` that can be compiled in jit code.
Additional allocation size for dynamic buffers will be calculated in
`RuntimeConfigurator`.*
 

### Tickets:
 - *123274*


### Prerequisites:
- https://github.com/openvinotoolkit/openvino/pull/24525

### TODO:
- [x] Add CPU support of dynamic offsets in memory access emitters
2024-06-10 08:04:29 +00:00
Nesterov Alexander a9cceb31b2
[DOCS] Update OpenVINO build instruction (Android system) (#24815) 2024-06-10 08:03:20 +00:00
Jorge Ragde 8646aff9e0
[TF FE] Support HSVToRGB operation for TensorFlow (#24875)
### Details:
- Using #24033, implemented and registered loader for HSVToRGB using
already existing logic.
 - Created unit test test_tf_HSVToRGB.py

### Tickets:
 - #24791 
 
Currently, my pytest is saying that for the unit test and for
test_tf_AdjustHue.py and test_tf_AdjustSaturation.py the loader is not
found.

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-06-10 07:56:08 +00:00
abushwang 79fc6bf79b
add support for opencloudos / tencentos (#24878)
There is so many developers are try to install openvino in opencloudos
and tencentos.
This pr add support for opencloudos / tencentos.

OpenCloudOS is an open source operating system community jointly
initiated by Tencent and its partners.

for more news:
https://www.opencloudos.org/
https://docs.opencloudos.org/en/

Signed-off-by: abushwang <abushwangs@gmail.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2024-06-10 13:05:26 +04:00
Ekaterina Aidova 1863f58a82
[PT FE]: support aten::hann_window (#24824)
### Details:
 - *aten::hann_window"

### Tickets:
 - *CVS-143016*

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-06-10 07:35:59 +00:00
dependabot[bot] 921e7c07b6
Bump reviewdog/action-shellcheck from 1.20.0 to 1.21.0 (#24918)
Bumps
[reviewdog/action-shellcheck](https://github.com/reviewdog/action-shellcheck)
from 1.20.0 to 1.21.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/reviewdog/action-shellcheck/releases">reviewdog/action-shellcheck's
releases</a>.</em></p>
<blockquote>
<h2>Release v1.21.0</h2>
<h2>What's Changed</h2>
<ul>
<li>chore(deps): update reviewdog/reviewdog to 0.17.5 by <a
href="https://github.com/github-actions"><code>@​github-actions</code></a>
in <a
href="https://redirect.github.com/reviewdog/action-shellcheck/pull/59">reviewdog/action-shellcheck#59</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/reviewdog/action-shellcheck/compare/v1.20.0...v1.21.0">https://github.com/reviewdog/action-shellcheck/compare/v1.20.0...v1.21.0</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="6e3a862f23"><code>6e3a862</code></a>
Merge pull request <a
href="https://redirect.github.com/reviewdog/action-shellcheck/issues/59">#59</a>
from reviewdog/depup/reviewdog/reviewdog</li>
<li><a
href="c82af54388"><code>c82af54</code></a>
chore(deps): update reviewdog/reviewdog to 0.17.5</li>
<li>See full diff in <a
href="72365a51bf...6e3a862f23">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=reviewdog/action-shellcheck&package-manager=github_actions&previous-version=1.20.0&new-version=1.21.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-06-10 07:26:59 +00:00
dependabot[bot] 90711b667a
Bump reviewdog/action-suggester from 1.12.0 to 1.13.0 (#24917)
Bumps
[reviewdog/action-suggester](https://github.com/reviewdog/action-suggester)
from 1.12.0 to 1.13.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/reviewdog/action-suggester/releases">reviewdog/action-suggester's
releases</a>.</em></p>
<blockquote>
<h2>Release v1.13.0</h2>
<h2>What's Changed</h2>
<ul>
<li>chore(deps): update reviewdog/reviewdog to 0.17.5 by <a
href="https://github.com/github-actions"><code>@​github-actions</code></a>
in <a
href="https://redirect.github.com/reviewdog/action-suggester/pull/55">reviewdog/action-suggester#55</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/reviewdog/action-suggester/compare/v1.12.0...v1.13.0">https://github.com/reviewdog/action-suggester/compare/v1.12.0...v1.13.0</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="9e1cd88b79"><code>9e1cd88</code></a>
Merge pull request <a
href="https://redirect.github.com/reviewdog/action-suggester/issues/55">#55</a>
from reviewdog/depup/reviewdog/reviewdog</li>
<li><a
href="2ebb5a11b1"><code>2ebb5a1</code></a>
chore(deps): update reviewdog/reviewdog to 0.17.5</li>
<li>See full diff in <a
href="185c9c06d0...9e1cd88b79">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=reviewdog/action-suggester&package-manager=github_actions&previous-version=1.12.0&new-version=1.13.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-06-10 07:26:36 +00:00
Ivan Tikhonov 72500f3e85
Handle 0 dims case in ReshapeOptimizations (#24879)
### Details:
The transformation works in 2 cases:
 * 1. all in/out dims are static, or we can match them via the symbols.
   2. only one out dim doesn't have the corresponding input static dim,
and we can't match it using symbols. Besides that the output shape must
not contain zero dims,
because then value -1 in 2nd input to Reshape op can't guarantee an
unambiguous determination of the remaining dim value.

### Tickets:
 - *CVS-143026*
2024-06-10 07:24:28 +00:00
Pawel Raasz bb75829a88
[core] Add f4e2m1 element type and float4_e2m1 type (#24863)
### Details:
 - Add new element into OpenVINO `f4e2m1`
 - Add new type `float4_e2m1`

### Tickets:
 - [CVS-141565](https://jira.devtools.intel.com/browse/CVS-141565)

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-06-10 07:15:45 +00:00
Sebastian Golebiewski 1144a66a9b
[DOCS] Updating interactive tutorials (#24886) 2024-06-10 05:34:50 +00:00
M aaa634874c
[GSOC][CPU][ARM] Activate SDPA for ARM devices (#24898)
### Details:
- This PR activates the Scaled Dot Product Attention (SDPA) operation on
ARM devices
2024-06-10 05:34:15 +00:00
Tingqian Li f5463512c6
[CPU] Add MLP & QKV fusion for LLM serving with PageAttention (#24837)
## Details:
in throughput oriented use case like vLLM, the computation bound of
Fullyconnect layers has a chance to become similar or even bigger than
memory-bound when batch-size is big, in such case, some optimization
opportunities was exploited in this PR:

### fusing multiple FC to get more computations per memory-read
- when split the problem `C=matmul(A, B)` among multi-cores, each core
has sub-problem of `subC=matmul(A, subB)`, with shapes:
    - A `[BM, K]`
    - subB `[K, BN]`
    - subC `[BM, BN]`

if we ignore subC matrix (since it's being loaded/stored only once
during `brgemm` procedure), the ratio of computations per memory-reads
is ` BM*K*BN / (BM*K + BN*K) = 1/(1/BM + 1/BN)`, and to get more
computations per memory-read, we prefer to increase this ratio, so we'd
like BN to be bigger (that's why we merge gate_FC with up_FC, and q_proj
with k_proj and v_proj).

in `down_proj`, there is no way to increase output channels (BN), we
split along K dimension once to reduce the number of splits of N, to
keep BN big too.

### prefetch sub-weight matrix to hide memory latency by computation

for execution of sub-problem `subC=matmul(A, subB)` on single core, we
further decompose it into sub-problems as following, to mix
SW-prefetching with AMX computations:

```python
for k0 in range(0, K, K_step):
     k1 = k0 + K_step
     blkB = subB[k0:k1, :]
     blkA = A[:, k0:k1]
     next_blkB = subB[k1:k1+K_step, :]
    # blkB's shape is [K_step, BN], which is L2 cache-able
    # inside following AMX based matmul jit kernel
    # we evenly scatter SW-prefetching instructions for next_blkB
    subC+=matmul_kernel(blkA, blkB, sw_prefetch = next_blkB) .
``` 

### flexible post-ops
jit-based post-Ops allows us to:
- interleaving fusion of weights of gate & up along N dimension in unit
of 16 fp32 elements, so post-op jit-kernel can combine them using
activation(like SiLU) while both results are hot in cache.
- QKV fusion requires final outputs was stored into 3 independent output
memories, special post-op jit kernel can do that easily.

### Tickets:
 - *ticket-id*

---------

Co-authored-by: Luo Cheng <cheng.luo@intel.com>
2024-06-10 05:09:26 +00:00
Evgenya Nugmanova a42da25019
Relaxes SharedOpOptimization restrictions (#24907)
### Details:
 - *Relaxes SharedOpOptimization restrictions on Constant comparison*

### Tickets:
 - *@vladimir-paramuzov*
2024-06-09 07:31:24 +00:00
Andrii Staikov 6e67110da1
[TRANSFORMATIONS] Extend PositionIDsReplacer pattern (#24890)
Extend PositionIDsReplacer pattern to support more models:
 - facebook/opt-350m

Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>

### Tickets:
 - CVS-143065

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2024-06-08 23:36:32 +00:00
Nesterov Alexander f6e6f2af56
[CPU][ARM] Support deconvolution to correctly handle multiple output edges on a single output port (#24754) 2024-06-07 17:32:26 +00:00
Alina Kladieva 45147aefa0
[GHA] dGPU tests pipeline (#24572)
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2024-06-07 15:22:07 +00:00
Sergey Shlyapnikov beb37eb4e1
[GPU] Move scaling from QK dot product to Q (#24896)
### Details:
- Move scaling from QK dot product to Q input for better SDPA accuracy
with high-value ranges

### Tickets:
 - [CVS-143256](https://jira.devtools.intel.com/browse/CVS-143256)
2024-06-07 13:04:12 +00:00
Gorokhov Dmitriy d996280d5e
[CPU] Cherry-pick IP optimizations from latest oneDNN master (#24654)
### Details:
- Downstream latest InnerProduct performance optimizations to oneDNN
fork
- Ticket:
[CVS-142995](https://jira.devtools.intel.com/browse/CVS-142995)
 - oneDNN fork PR: https://github.com/openvinotoolkit/oneDNN/pull/252
2024-06-07 12:53:38 +00:00
Alexandra Sidorova 2893f2fc7c
[Snippets] Added dynamism support to MHA Tokenization pass (#24897)
### Details:
- *Updated `MHATokenization` pass to support dynamic nodes tokenization*
 - *Added MHATokenization unit tests*
 - *Disabled dynamic MHA tokenization in CPU Plugin*


### Tickets:
 - *123329*
2024-06-07 12:13:26 +00:00
Anastasia Kuporosova ba5c45a4ee
[PyOV] Fix hanging on infer request destruction (#24722)
### Details:
- Initial problem: `test_custom_op` hanged on destruction because it was
waiting for a thread which tried to acquire GIL.
- The second problem is that pybind11 doesn't allow to work with GIL
besides of current scope and it's impossible to release GIL for
destructors. https://github.com/pybind/pybind11/issues/1446
- Current solution allows to release GIL for InferRequest and all called
by chain destructors.

### Tickets:
 - CVS-141744
2024-06-07 11:56:36 +00:00
Tatiana Savina bb179c69d1
[DOCS] CPU perf hints doc review (#24827)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-06-07 11:46:26 +00:00
Evgenya Nugmanova c542405470
More accurate shape of optimization (#24845)
### Details:
- *Topological order was corrected to perform the best ShapeOf
reconnections possible*

### Tickets:
 - *CVS-142953*
2024-06-07 10:34:53 +00:00
Karol Blaszczak 5faf95018d
[DOCS] fix back to top button (#24884) 2024-06-07 10:28:41 +00:00
Andrii Staikov 852878162d
[TRANSFORMATIONS] Add a check to SDPAToPagedAttention to fail fast (#24841)
[TRANSFORMATIONS] Add a check to SDPAToPagedAttention to fail fast

Add a check to SDPAToPagedAttention to fail fast if no
ScaledDotProductAttention operation present in a graph hence no
transformation will be executed.

### Tickets:
 - CVS-143067

Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>

---------

Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2024-06-07 08:23:27 +00:00
Tomasz Jankowski 7f1ddd55ac
[Core/Ref] Resolve coverity issues (#24874)
### Details:
 - Fixed coverity issues in src/core/reference

### Tickets:
 - CVS-143152
2024-06-07 08:14:32 +00:00
zhaohongbo 236e1062b2
[CPU] Optimize the unique operator (#24850)
### Details:
 - *Optimize  unique using HashMap when sorted=false*
 - *...*

### Tickets:
 - *ticket-id*
2024-06-07 07:06:10 +00:00
Mingyu Kim d286268a85
[GPU][DOC] Link to OCL article (#24813) 2024-06-07 06:38:58 +00:00
hyunback kim faa19e6121
[GPU] Fix wrong condition for dynamic onednn convolution impl-type. (#24497)
Remove the limitation that oneDNN convolution doesn't support dynamic
input and output.
With this limitation, clDNN convolution will run forever in dpas
platform.
Because oneDNN Opt convolutions require blocked-format and current shape
agnostic convolution doesn't support block-format, convolution do
nothing in compile_graph stage and actual kernel compilation will happen
at first inference.

### Tickets:
 - *141040*

Signed-off-by: hyunback <hyunback.kim@intel.com>
2024-06-07 06:32:38 +00:00
Alexandra Sidorova 00510e69fd
[Snippets] Fixed Invalid Read in FuseLoops pass (#24880)
### Details:
- *Fixed Invalid Read in FuseLoops pass. Before we save loop ports by
reference from `current_loop_info`. However, this `current_loop_Info`
might be changed (another shared pointer) and the previous saved loop
ports by reference are invalid (the original `current_loop_info` is
expired)*
 - *`Valgrind` doesn't throw exception anymore with this fix*

### Tickets:
 - *N/A*
2024-06-07 06:29:01 +00:00
barnasm1 416c4ffb7e
[CORE] depracate get/set_concatenation_axis functions (#24737)
### Details:
 - remove `set_concatenation_axis` function usage
 - replace `get_concatenation_axis` function usage

### Tickets:
- [CVS-94507](https://jira.devtools.intel.com/browse/CVS-94507)

### Related PR:
 - https://github.com/openvinotoolkit/openvino/pull/24383

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-06-07 05:55:52 +00:00
Vladimir Paramuzov 0cc051debb
[GPU] Don't add crop for unused out ports of Split op (#24877)
### Details:
- Currently we insert crop primitive for each out port of
(Variadic)Split ops, and if some of them are not used we just waste some
execution time. This patch modifies converter for Split to process ports
with real users only.
2024-06-07 05:53:13 +00:00
Maxim Vafin b8ced3dfc7
Change opt-125m-gptq model (#24899)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-06-07 14:50:30 +04:00
dependabot[bot] 4fcfaf24b3
Bump actions/dependency-review-action from 4.3.2 to 4.3.3 (#24876)
Bumps
[actions/dependency-review-action](https://github.com/actions/dependency-review-action)
from 4.3.2 to 4.3.3.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/actions/dependency-review-action/releases">actions/dependency-review-action's
releases</a>.</em></p>
<blockquote>
<h2>Notes for v4.3.3</h2>
<h2>What's Changed</h2>
<ul>
<li>Allow slashes in purl package names by <a
href="https://github.com/juxtin"><code>@​juxtin</code></a> in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/765">actions/dependency-review-action#765</a></li>
<li>use the v3 version of the deps.dev API by <a
href="https://github.com/josieang"><code>@​josieang</code></a> in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/741">actions/dependency-review-action#741</a></li>
<li>PR with suggestions - [Improvement]: Help streamline / simplify
dependency review action README by <a
href="https://github.com/am-stead"><code>@​am-stead</code></a> in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/773">actions/dependency-review-action#773</a></li>
<li>fix show-openssf-scorecard-levels input by <a
href="https://github.com/ramann"><code>@​ramann</code></a> in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/776">actions/dependency-review-action#776</a></li>
<li>Updates to the contribution guidelines by <a
href="https://github.com/jonjanego"><code>@​jonjanego</code></a> in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/778">actions/dependency-review-action#778</a></li>
<li>Create issue templates by <a
href="https://github.com/jonjanego"><code>@​jonjanego</code></a> in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/777">actions/dependency-review-action#777</a></li>
<li>Fix the max comment length issue by <a
href="https://github.com/jhutchings1"><code>@​jhutchings1</code></a> and
<a href="https://github.com/elireisman"><code>@​elireisman</code></a> in
<a
href="https://redirect.github.com/actions/dependency-review-action/pull/767">actions/dependency-review-action#767</a></li>
<li>Bump project version to 4.3.3 in prep for a release by <a
href="https://github.com/elireisman"><code>@​elireisman</code></a> in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/781">actions/dependency-review-action#781</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a href="https://github.com/josieang"><code>@​josieang</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/741">actions/dependency-review-action#741</a></li>
<li><a href="https://github.com/am-stead"><code>@​am-stead</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/773">actions/dependency-review-action#773</a></li>
<li><a href="https://github.com/ramann"><code>@​ramann</code></a> made
their first contribution in <a
href="https://redirect.github.com/actions/dependency-review-action/pull/776">actions/dependency-review-action#776</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/dependency-review-action/compare/v4.3.2...v4.3.3">https://github.com/actions/dependency-review-action/compare/v4.3.2...v4.3.3</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="72eb03d02c"><code>72eb03d</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/dependency-review-action/issues/781">#781</a>
from actions/release-v4.3.3</li>
<li><a
href="137d8b42ce"><code>137d8b4</code></a>
bump to version v4.3.3</li>
<li><a
href="e6b618ed05"><code>e6b618e</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/dependency-review-action/issues/767">#767</a>
from actions/max-comment-length</li>
<li><a
href="3c42649204"><code>3c42649</code></a>
fix ws for linter</li>
<li><a
href="8e6ea8d29b"><code>8e6ea8d</code></a>
update packaging</li>
<li><a
href="1b3d2772d0"><code>1b3d277</code></a>
post-review: add PR comment full summary test case</li>
<li><a
href="220872c81a"><code>220872c</code></a>
Update src/main.ts</li>
<li><a
href="087d0f81a5"><code>087d0f8</code></a>
repackage to update dist</li>
<li><a
href="4531204be7"><code>4531204</code></a>
whitespace</li>
<li><a
href="df1ca890c5"><code>df1ca89</code></a>
appease linter</li>
<li>Additional commits viewable in <a
href="0c155c5e85...72eb03d02c">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=actions/dependency-review-action&package-manager=github_actions&previous-version=4.3.2&new-version=4.3.3)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-06-06 07:22:33 +00:00
Sebastian Golebiewski b9e1ef7486
[DOCS] Updating Nodejs API with descriptions (#24866)
Adding descriptions of methods to Node.js API.
2024-06-06 06:58:31 +00:00
Tomasz Jankowski 11ad74dcda
[Core/test] Resolve TODOs in chech_opset1 (#24819)
### Details:
- Removed potential tests of operator which won't be added to opset 1
(as it's frozen),
 - enabled those which are present.
 - Renamed function.

### Tickets:
 - n/a

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-06-06 05:02:37 +00:00
Xiping Yan e922edf299
Add test case to verify 4bit precision input model. (#24774)
### Details:
- *Complete the remaining work after the
[PR](https://github.com/openvinotoolkit/openvino/pull/24297) is merged.*
 - *Add test case.*

### Tickets:
 - *141542*

---------

Signed-off-by: xipingya <xiping.yan@intel.com>
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
2024-06-06 03:23:26 +00:00
David Nam b1bc59e72d
[GPU] Fix Loop to cover the case where memory is null at the first iteration (#24776)
### Details:
 - Handle the case where from_mem is null at the first iteration 

### Tickets:
 - 141652
2024-06-05 21:49:34 +00:00
Attila Csok 9d208241f0
[intel-npu] Adding new properties to tests (#24865)
### Details:
- Adding missing property tests to npuFuncTests: EXECUTION_MODE_HINT,
DEVICE_TYPE, PCI_INFO and DEVICE_GOPS

### Tickets:
 - none
2024-06-05 18:48:13 +00:00
Tomasz Jankowski a156b69ccc
[Core] Deprecate ambiguous ov::element::Type ctor (#24698)
### Details:
 - Added deprecation mark to ambiguous ov::element::Type ctor

(https://github.com/openvinotoolkit/openvino/pull/11211#discussion_r834939746)
### Tickets:
 - CVS-133840

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-06-05 18:30:41 +00:00
Zlobin Vladimir 00d525f5a2
Export OpenVINOGenAI_DIR (#24683) (#24870)
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2024-06-05 22:43:26 +04:00
Mikhail Ryzhov 13922e7515
[GHA] Win-CC decrease build jobs (#24869)
### Details:
Without thread limitation win-cc pipeline fails with run out of memory
error:

https://github.com/openvinotoolkit/openvino/actions/runs/9384908136

set 16 threads

### Tickets:
 - *ticket-id*
2024-06-05 17:10:04 +00:00
rghvsh c87cf86489
[ONNX] Align behavior of ONNX Frontend operator ReduceMean-11, 13, 18 with original framework (#23148)
### Details:
- Align behavior of ONNX Frontend operator ReduceMean-11, 13, 18 with
original framework

### Tickets:
 - Closes https://github.com/openvinotoolkit/openvino/issues/20556

---------

Co-authored-by: Georgy Krivoruchko <georgy.krivoruchko@intel.com>
2024-06-05 13:30:37 +00:00
Tomasz Jankowski de4d00a597
[Core] Fix coverity issues (#24838)
### Details:
 - Used move instead of copy.

### Tickets:
 - CVS-121621
2024-06-05 12:12:57 +00:00
Mikhail Ryzhov 41d460f7ac
[GHA] Pinned MSVC toolset version (#24860)
### Details:
 - Pinned MSVC toolset version
 - removed hardcoded jobs count
 
### Tickets:
 - *ticket-id*
2024-06-05 12:10:14 +00:00
Yamini Nimmagadda 9e662351e8
torch.compile documentation updates for 2024.2 (#24803)
### Details:
 - Updated 'How to Use' and 'Options' sections
 - Added quantization and torchserve sections

---------

Co-authored-by: Mustafa Cavus <mustafa.cavus@intel.com>
Co-authored-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2024-06-05 08:33:04 +00:00
Mikhail Ryzhov aa04a9bcfa
[WIN-CC] Support the latest msvc (19.40) (#24849)
### Details:
 - Aligned build jobs with runner configuration to speed up the build
- added temporary variable data_type to resolve internal compilation
error with the new msvc (19.40)

https://jira.devtools.intel.com/browse/CVS-142993

### Tickets:
 - *ticket-id*
2024-06-05 08:32:25 +00:00
Alicja Miloszewska cf22524dcb
[OV JS] Add methods descriptions for Model, Tensor & InferRequest (#24768)
### Details:
 - Add methods descriptions for Model, Tensor & InferRequest

---------

Co-authored-by: Maciej Smyk <maciejx.smyk@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-06-05 07:37:00 +00:00
Chen Xu dd0846b8d5
[CPU] [Snippets] Fix performance regression in calling parallel_nt (#24832)
### Details:
- *This PR fixes geomean level performance issue caused by
https://github.com/openvinotoolkit/openvino/pull/23180 on platforms with
sufficient cores.*
- *In the PR mensioned above, `parallel_nt` is used for executing
subgraph instead of `parallel_for5d`, becuase the former has performance
advantage for the case where #tasks is more than #threads*. That is
becuase using `parallel_nt`, we can initilize parameters for each
thread, while parameters are initilized for each task in using
`parallel_for5d`. So `parallel_nt` has less overheads.
- *However, for the case where #tasks is less than #threads,
`parallel_nt` brings performance regression. Because compared with
`parallel_for5d`, `parallel_nt` doesn't apply the argument
`tbb::static_partitioner{}` when calling `tbb::parallel_for`. Here we
use `parallel_nt_static` instead to fix the performance regression.*
2024-06-05 07:27:36 +00:00
Vladimir Paramuzov f952f73d6b
[GPU] Fix decompression scales reorder when data is reused (#24842)
### Details:
- In case when scale tensor was used by multiple compressed FCs we had
an exception on attempt to insert reorder between them. This patch
changes reorder name so now multiple reorders are inserted for each
Scale+FC pair, and then on later stages we merge them if they do same
tensor transform.
2024-06-05 06:10:37 +00:00
Roman Lyamin adb590d5f4
[GPU] Added RoPE support for Llama2, Llama3 and Phi-3 (#24829)
### Tickets:
 - *[119150](https://jira.devtools.intel.com/browse/CVS-119150)*
 - *[141777](https://jira.devtools.intel.com/browse/CVS-141777)*
2024-06-04 22:16:48 +00:00
Georgy Krivoruchko c45a46edca
[TFLite] Added implementation details (#24835)
### Details:
 - Added an implementation details for sparse-tensors reading

### Tickets:
 - N/A

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-06-04 18:49:05 +00:00
Andrei Kashchikhin 52d0a44d3f
[CI] [GHA] Set actions references to specific commit hash; provide explicit top level token permissions for jobs (#24839)
### Details:
- Token permissions docs:
98ec491a88/docs/checks.md (token-permissions)
- Actions by hash docs:
98ec491a88/docs/checks.md (pinned-dependencies)

### Tickets:
 - *142943*
 - *142944*
2024-06-04 18:17:51 +00:00
Roman Kazantsev 65b5b8e1b7
[MOC] Implement EliminateLoopInputsOutputs (#24786)
**Details:** EliminateLoopInputsOutputs transformation helps to avoid an
isolated sub-graphs `Parameter->Result` in a body graph of `Loop` and
`TensorIterator`. Such sub-graphs are useless and can by-pass `Loop`
operation.

**Ticket:** 142440

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Evgeny Kotov <evgeny.kotov@intel.com>
Co-authored-by: Tikhonov Ivan <ivan.tikhonov@intel.com>
2024-06-04 12:37:16 +00:00
Andrew Kwangwoong Park 1a70c4002c
[GPU] Optimize RMS kernel (#24831)
### Details:
 - Optimize RMS kernel by subgroup block IO
 - Compute maximum possible LWS and the number of data in subgroups
- Add test cases which covers leftover handling and unaligned data shape

### Tickets:
 - 141845

---------

Signed-off-by: Andrew Park <andrew.park@intel.com>
2024-06-04 11:02:12 +00:00
Luo Cheng d954a80161
[CPU] Add inplace and jit for ROPE (#24788)
### Details:
 - *Add inplace and jit if possible*
 - *...*

### Tickets:
 - *ticket-id*
2024-06-04 10:20:18 +00:00
Karol Blaszczak a23c9d5b5a
[DOCS] benchmark data for LLM master (#24834) 2024-06-04 09:25:38 +00:00
Razvan Apetroaie 1a6ddfff60
[NPU] Add the "create_executor" property inside the Plugin's list as well (#24828)
### Details:
- `ov::intel_npu::create_executor` is declared a supported property only
for the `intel_npu::CompiledModel` class. The current PR adds an entry
inside `intel_npu::Plugin` as well.

### Tickets:
 - *CVS-143060*
2024-06-04 09:19:21 +00:00
Brett Jia f1862e4d20
build: fix Python platform architecture tag for armv7l (#24772)
On arm32 (armv7), the platform tag should be `armv7l` as per
https://peps.python.org/pep-0599/
2024-06-04 12:54:20 +04:00
Roman Lyamin df6a25800d
[GPU] Added RoPE support for ChatGLM and Qwen (#24756)
### Details:
- Added support RoPE for ChatGLM and Qwen models
- Moved and refactored RoPE functional tests

### Tickets:
 - *[119150](https://jira.devtools.intel.com/browse/CVS-119150)*
2024-06-03 10:34:13 +00:00
Sergey Shlyapnikov ba8d6c5de5
[GPU] SDPA minor improvements (#24770)
### Details:
- Change the default softmax accumulator type from FP16 to FP32 (this
doesn't affect performance, as well as accuracy at first glance;
however, let's stick to higher precision here)
- Applied review comments from PR
https://github.com/openvinotoolkit/openvino/pull/24466
- Minor internal operations refactoring (SDPA and IndirectSDPA)
- Add new tests for GQA optimization and for indirect inputs
2024-06-03 10:34:13 +00:00
Taylor Yeonbok Lee cea8e1f5e4
[GPU] Fixed unexpected kv cache optimization turned off (#24805)
### Details:
- kv cache opt was disabled due to the wrongly detected beam table size.
Fixed this issue.
### Tickets:
 - *ticket-id*
2024-06-03 10:34:13 +00:00
Katarzyna Mitrus 142114ccbc
[Op] Squeeze update - no throw on non-squeezable dims (#24715)
### Details:
- Changes needed to enable Squeeze (and models) with axes pointing to
non-squeezable dims (currently ov throws an error for such case) -
considered as backward compatible change
- If agreed to update functionality within the same version of the op,
actual changes are needed only in shape infer related functions to cover
**Template, CPU and GPU plugins**:
    -  src/core/shape_inference/include/squeeze_shape_inference.hpp
    -  src/plugins/intel_cpu/src/shape_inference/custom/reshape.cpp
    -  The rest of the changes are test related.
 - Pytorch FE Squeeze test enabled - passed

### Tickets:
 - 142387
2024-06-03 09:59:07 +00:00
Alicja Miloszewska 56d184dbb1
[OV JS] Add method descriptions for Core (#24693)
### Details:
 - Add method descriptions to TS for Core

### Tickets:
 - *141290*

---------

Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
2024-06-03 07:31:07 +00:00
Alexandra Sidorova f859992efe
[Tests] Fixed debug info about ranges (#24790)
### Details:
- *Removed Debug info printing by default from
https://github.com/openvinotoolkit/openvino/pull/23428*
 ```
[ RUN ]
smoke_Snippets_Softmax/Softmax.CompareWithRefImpl/IS=[?.?]_TS=((1.16))_((1.32))_((1.1))_((1.9))_((1.17))_((1.19))_((1.49))_((1.50))_((5.16))_((1.16))_((1.9))_Axis=-1_#N=1_#S=1_targetDevice=CPU

MEM_USAGE=3007144KB
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
RANGE FOR PARAMETER: Parameter_1590025 start from: 0.000000 range: 8
resolution: 32 seed: 1
[ OK ]
smoke_Snippets_Softmax/Softmax.CompareWithRefImpl/IS=[?.?]_TS=((1.16))_((1.32))_((1.1))_((1.9))_((1.17))_((1.19))_((1.49))_((1.50))_((5.16))_((1.16))_((1.9))_Axis=-1_#N=1_#S=1_targetDevice=CPU
(132 ms)
 ```

### Tickets:
 - *N/A*
2024-06-03 10:56:36 +02:00
Roman Kazantsev 3497133dc4
[TF FE] Xfail test for Rint on arm (#24810)
**Details:** In pre-commit we observe sporadic failure of Rint test on
arm

**Tickets:** TBD

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-06-03 12:12:42 +04:00
Evgenya Nugmanova fc0b82c1be
[SDPA] relax restriction on L from query and attention_mask being equal (#24745)
### Details:
 - *relax restriction on L from query and attention_mask being equal*

### Tickets:
 - *CVS-129000*
2024-06-03 05:08:53 +00:00
Jade Cho 5a8d75d076
[GPU] Update oneDNN v3.5 (#24787) 2024-06-03 09:35:28 +04:00
duydl 5ea0e96fc2
[TF FE] Support AdjustHue operation (#24769)
### Details:
- Adapt from #24511 . Converting code repeated. Instead import from
there?
- Converting logic a little different from
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/kernels/image/adjust_hue_op.cc
. Maybe less efficient?

### Tickets:
 - #24033 

Sorry, commit history is wrong, should have created branch from latest
upstream.

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-06-03 00:09:09 +04:00
Maciej Smyk 3ffac369f1
[DOCS] Moving images from index.rst for master (#24798)
Moved images included in index.rst article to articles_en/assets folder.
2024-05-31 13:12:31 +00:00
Wanglei Shen ee0a025ca0
[DOCS] introduce performance hint and threads scheduling in CPU inference (#24147)
### Details:
 - *introduce performance hint and threads scheduling in CPU inference*

### Tickets:
 - *CVS-138834*

---------

Co-authored-by: Sun Xiaoxia <xiaoxia.sun@intel.com>
2024-05-31 11:58:30 +00:00
Sofya Balandina b86fbf8951
[ov_api_conformance] Remove hetero tests as it will be covered by sw device run over template (#24752)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-31 11:37:24 +00:00
dependabot[bot] 5f446b5ebb
Bump py-cpuinfo from 7.0.0 to 9.0.0 in /tests (#24696)
Bumps [py-cpuinfo](https://github.com/workhorsy/py-cpuinfo) from 7.0.0
to 9.0.0.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/workhorsy/py-cpuinfo/blob/master/ChangeLog">py-cpuinfo's
changelog</a>.</em></p>
<blockquote>
<ul>
<li>Release 9.1.0
<ul>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/186">#186</a>:
Move to Python 3 style classes and default UTF-8 encoding</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/194">#194</a>:
Add support for LoongArch</li>
</ul>
</li>
</ul>
<p>10/25/2022 Release 9.0.0</p>
<ul>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/178">#178</a>:
Changes to lscpu breaks parsing of cache info</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/152">#152</a>:
CPU stepping, model, and family values are blank if 0</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/177">#177</a>:
Officially drop support for Python 2</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/171">#171</a>:
Replace Python 3.11 deprecated unittest.makeSuite</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/173">#173</a>:
Fix lgtm.com alerts</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/165">#165</a>:
Support Wheel</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/167">#167</a>:
Add support for RISC-V</li>
</ul>
<p>04/14/2021 Release 8.0.0</p>
<ul>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/161">#161</a>:
Accept arm64 as an alias for aarch64</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/160">#160</a>:
Add MIPS architecture support</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/74">#74</a>:
Add option to trace code paths to file</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/157">#157</a>:
Remove multiple checks for sestatus</li>
</ul>
<p>07/05/2020 Release 7.0.0</p>
<ul>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/133">#133</a>:
CPU flags vary between runs on Mac OS X</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/150">#150</a>:
Change 'byte code' to 'machine code'</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/128">#128</a>:
Overhead from generating machine code throws off CPUID HZ</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/136">#136</a>:
On non BeOS systems, calling sysinfo may open GUI program</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/138">#138</a>:
Invalid escape sequences warn when building in Python 3.8</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/147">#147</a>:
Remove extended_model and extended_family fields</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/146">#146</a>:
CPUID family and model is wrong</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/144">#144</a>:
Cache fields should be full ints instead of kb strings</li>
</ul>
<p>06/11/2020 Release 6.0.0</p>
<ul>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/140">#140</a>:
The get_cache function has swapped fields</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/142">#142</a>:
Remove empty and zeroed fields</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/115">#115</a>:
Missing data on Ryzen CPUs</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/122">#122</a>:
Rename fields to be more clear</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/125">#125</a>:
Add option to return --version</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/126">#126</a>:
Make test suite also check SELinux</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/120">#120</a>:
Make unit tests also test CPUID</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/69">#69</a>:
Add s390x support</li>
</ul>
<p>03/20/2019 Release 5.0.0</p>
<ul>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/117">#117</a>:
Remove PyInstaller hacks</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/108">#108</a>:
Client script runs multiple times without <strong>main</strong></li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/113">#113</a>:
Add option to return results in json</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/110">#110</a>:
Always tries to run wmic in get_system_info.py</li>
</ul>
<p>04/01/2018 Release 4.0.0</p>
<ul>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/80">#80</a>:
Broken when using Pyinstaller</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/77">#77</a>:
Get L1, L2, and L3 cache info from lscpu</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/79">#79</a>:
Byte formats are inconsistent</li>
<li>Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/81">#81</a>:
Byte formatter breaks on non strings</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="4824ec0746"><code>4824ec0</code></a>
Release 9.0.0</li>
<li><a
href="45b5144505"><code>45b5144</code></a>
Merge pull request <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/182">#182</a>
from workhorsy/lscpu_changes</li>
<li><a
href="850e2a0817"><code>850e2a0</code></a>
Merge branch 'master' into lscpu_changes</li>
<li><a
href="a93e04dea7"><code>a93e04d</code></a>
Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/178">#178</a>:
Changes to lscpu breaks parsing of cache info</li>
<li><a
href="21e4f3b2af"><code>21e4f3b</code></a>
Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/152">#152</a>:
CPU stepping, model, and family values are blank if 0</li>
<li><a
href="54e62b796d"><code>54e62b7</code></a>
Added new test that breaks from lscpu changes</li>
<li><a
href="635811dcdd"><code>635811d</code></a>
Merge pull request <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/179">#179</a>
from workhorsy/bye_bye_py2</li>
<li><a
href="5dffea059b"><code>5dffea0</code></a>
Fixed Bug <a
href="https://redirect.github.com/workhorsy/py-cpuinfo/issues/177">#177</a>:
Officially drop support for Python 2</li>
<li><a
href="07eab4ddfb"><code>07eab4d</code></a>
Update build script to build python 3 wheel instead of python 2 and 3
wheel</li>
<li><a
href="f7075479e7"><code>f707547</code></a>
Updated info in readme</li>
<li>Additional commits viewable in <a
href="https://github.com/workhorsy/py-cpuinfo/compare/v7.0.0...v9.0.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=py-cpuinfo&package-manager=pip&previous-version=7.0.0&new-version=9.0.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-05-31 09:07:00 +00:00
Edward Shogulin 33bbfd1883
[CPU] [ARM] JIT Floor (#24041)
### Details:
 - *[CPU] [ARM] jit floor*

### Tickets:
 - *CVS-138572*
2024-05-31 05:31:07 +00:00
Mingyu Kim b669e232c8
[GPU] Do not use shape-agnostic kernel for OneDNN FC fp16 (#24702)
### Details:
 - WA of out-of-bound access for fc kernel.
- Use OneDNN FC kernel for fp16 FC when possible. It hides the issue
because the target platform can use OneDNN.
- For shape-agnostic kernel, TILE_B=8 is chosen. It causes out-of-bound
memory access for LLM 2nd token.

### Tickets:
 - 142277
2024-05-31 01:51:40 +00:00
Bo Liu cf08511954
[CPU][FP16] Migrate from EnfornceInferencePrecision to ConvertPrecision (#23950)
### Details:
- *Migrate FP16 operations mark-up from `EnforceInferencePrecision`
utility to `ConvertPrecision` pass*


### Tickets:
 - *128875*

---------

Co-authored-by: Egor Duplensky <egor.duplensky@gmail.com>
2024-05-31 01:27:45 +00:00
Alexandra Sidorova 2d0e0366f7
[Snippets] United Static and Dynamic Loops into one node (#24525)
### Details:
- *United `LoopEndStatic` and `LoopEndDynamic` into one node `LoopEnd`
to avoid extra conditions in the code and improve performance since some
pointer data shifts might be known and compiled in JIT code*
- *Removed dynamic aarch64 loop emitters since they don't work anyway
CVS-141550*
- *Added support dynamism to `IdentifyBuffers` and
`DefineBufferClusters`. It's not efficient algorithm since we don't know
exact values of data pointer shifts and cannot be sure that they will be
proportionally in runtime. It should be implemented as the separate
feature based on some judgments, for example*

### Tickets:
 - *141268*


### Prerequisites:
- *https://github.com/openvinotoolkit/openvino/pull/21922*
2024-05-30 14:07:46 +00:00
Andrei Kashchikhin 5104769953
[CI] [GHA] Add `Unable to fetch some archives` to errors to look for file (#24782)
### Tickets:
 - *130965*
2024-05-30 13:29:40 +00:00
Ivan Tikhonov 817a835f0a
Do not convert Squeeze/Unsqueeze to Reshape in Symbolic transformations (#24771)
### Details:
Disable EliminateSqueeze/EliminateUnsqueeze passes in
SymbolicOptimizations

### Tickets:
 - *CVS-141814*

---------

Co-authored-by: Evgenya Nugmanova <eva.my.link@gmail.com>
Co-authored-by: Evgenya Nugmanova <evgeniia.nugmanova@intel.com>
2024-05-30 11:20:28 +00:00
Ivan Tikhonov ce7db95d8a
Use Slice operation directly on CPU and update RoPE patterns (#24379)
### Details:
 - SliceToStridedSlice was moved from MOC to Common transformations.
 - Updated RoPE fusion patterns
 - 2 new transformations:  EliminateSlice, SliceSequenceToSingleSlice
- Updated EliminateStridedSlice transformation to support int32_max
case, deleted transformation duplicate from CPU
 - Added new unit tests

Tested locally with these models:

- [x] Means that Model compilation passed, and all RoPE related
transformations were applied in the same order
- [x] hf-internal-testing/tiny-random-StableLmForCausalLM
- [x] hf-internal-testing/tiny-random-FalconForCausalLM
- [x] hf-internal-testing/tiny-random-Starcoder2ForCausalLM
- [x] hf-internal-testing/tiny-random-LlamaForCausalLM
- [x] hf-internal-testing/tiny-random-GPTNeoXForCausalLM
- [x] hf-internal-testing/tiny-random-GPTJForCausalLM
- [x] hf-internal-testing/tiny-random-CodeGenForCausalLM
- [x] hf-internal-testing/tiny-random-MistralForCausalLM
- [x] hf-internal-testing/tiny-random-PhiForCausalLM
- [x] Qwen/Qwen1.5-7B
- [x] THUDM/chatglm3-6b
- [x] EleutherAI/gpt-neox-20b
- [x] google/gemma-2b-it
- [x] EleutherAI/gpt-j-6b
- [x] meta-llama/Meta-Llama-3-8B
- [x] mistralai/Mistral-7B-v0.1

### Tickets:
 - *CVS-126971*
2024-05-30 10:33:58 +00:00
Evgenya Nugmanova a5e9737bab
[PyOV] Added symbolic propoagation to model visualization to enhance OV developer experience (#24763)
### Details:

As a result, you can use this code for most of your needs:

- in a Jupiter notebook
- as a cmd tool
- with model weights being far away

```
def configure_visualizer(enable=True, max_const_elements=7):
    # parameter max_const_elements manipulates the number of first elements of a constant that will be serialized
    # to svg. Put 0 if the model is on a share
    import os
    envs_to_set = [
        'OV_VISUALIZE_TREE_IO',
        'OV_VISUALIZE_TREE_OUTPUT_SHAPES',
        'OV_VISUALIZE_TREE_OUTPUT_TYPES',
        'OV_VISUALIZE_TREE_EDGE_LABELS',
        # symbolic information and partial values
        'OV_VISUALIZE_APPLY_SYMBOLIC_PROPAGATION',
        'OV_VISUALIZE_PARTIAL_VALUES_AND_LABELS'
    ]
    for e in envs_to_set:
        os.environ[e] = '1' if enable else '0'
    os.environ["OV_VISUALIZE_TREE_CONST_MAX_ELEMENTS"] = str(max_const_elements) if enable else "7"


def serialize_model_to_svg(model, output_name='serialized_model.svg'):
    from openvino.runtime.passes import VisualizeTree
    configure_visualizer(True)
    VisualizeTree(output_name).run_on_model(model)
    configure_visualizer(False)


def convert_model_to_svg(input_name, output_name=None):
    import openvino as ov
    core = ov.Core()
    model = core.read_model(input_name)
    if output_name is None:
        output_name = os.path.splitext(os.path.basename(input_name))[0] + '.svg'
    serialize_model_to_svg(model, output_name)


if __name__ == "__main__":
    import sys, os

    arguments = sys.argv[1:]
    if len(arguments) not in [1, 2]:
        print(f"Usage {sys.executable} {__file__} /path/to/model [output_file_name.svg]")
        sys.exit(1)
    output_file = os.path.splitext(os.path.basename(arguments[0]))[0] + '.svg' if len(arguments) == 1 else arguments[1]
    convert_model_to_svg(arguments[0], output_file)
```
2024-05-30 10:03:51 +00:00
Andrei Kashchikhin 10177bfb89
[CI] [GHA] Introduce Dockerfiles for test jobs (#24742)
### Tickets:
 - *141574*
2024-05-30 09:46:12 +00:00
Yury Gaydaychuk 522a3c6a7d
[CPU] Nodes errors handling moved to graph (#24161)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *136887*
2024-05-30 09:23:05 +00:00
JJJohnathan 48f64b6086
[AUTO] Fix memory leak in ov_auto_unit_tests (#24372)
SharedPtr mutual reference fix
### Details:
- use lambda function replacing "Return" function of Gmock in ON_CALL
for *mockIExeNet.get()
- use lambda function replacing "Return" function of Gmock in ON_CALL
for *mockIExeNetActual.get()

"Retrun" function would cause increment of use account of
inferReqInternal and inferReqInternalActual, thereby causing mutual
reference of SharedPtr between mockIExeNet and inferReqInternal or
mockIExeNetActual and inferReqInternalActual.

### Ticket:
   - [CVS-134423](https://jira.devtools.intel.com/browse/CVS-134423)
2024-05-30 09:01:07 +00:00
Andrii Staikov be5fd8b6d4
Add PagedAttention tests to Precommit (#24634)
### Details:
Add tests for the SPDAToPagedAttention transformation to Precommit
1) Check if PagedAttentionExtension node appeared in the model after the
transformation
2) Check 2 last dimensions of 'key_cache.' and 'value_cache.' inputs to
be static.

### Tickets:
 - [CVS-138943](https://jira.devtools.intel.com/browse/CVS-138943)

Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>
2024-05-30 08:58:09 +00:00
Xuejun Zhai 830f56e343
[Windows][Unicode] wstring to string in windows failed (#24606)
### Details:
- Windows std::wstring convert to std::string some unicode will be ???,
such as L"unicode_Яㅎあ" -> "unicode_???"

### Tickets:
 - CVS-141444
 - CVS-141729

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
2024-05-30 08:52:58 +00:00
Mingyu Kim ed09df8adf
[GPU] Reduce the condition for not-using usm-host input buffer (#24761)
### Details:
 - Reduce the condition for not-using usm-host input buffer
- This is to reduce the overhead in next-gen GPU performance where
usm_host is the input buffer

### Tickets:
 - 141493
2024-05-30 05:55:00 +00:00
Taylor Yeonbok Lee cb9c5216ab
[GPU] Fixed beam search scenario for first input is not batched (#24625)
### Details:
- Fixed crash & accuracy issue in beam search scenario when initial
input is not batched

### Tickets:
 - 140755
2024-05-30 01:10:00 +00:00
Sofya Balandina bcd96048b3
[ov_subgraphs_dumper_tests] Fix memory leaks (#24751)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *CVS-134419*
2024-05-29 17:16:34 +00:00
Sergey Shlyapnikov cfb5d4ee84
[GPU] Enable SDPA optimization by default (#24767)
### Details:
This PR is a copy of
https://github.com/openvinotoolkit/openvino/pull/24757 from release
branch, it includes:
- Enabled SDPA by default
- Updated SDPA decomposition rule to cover only well-checked cases
- Updated functional tests accordingly
2024-05-29 16:36:42 +00:00
Edward Shogulin 45e219b450
[LPT] EliminateFakeQuantizeTransformation: bf16 support (#24755)
### Details:
 - *[LPT] EliminateFakeQuantizeTransformation: bf16 support*

### Tickets:
 - *CVS-138910*
2024-05-29 15:21:19 +00:00
Ivan Tikhonov b16108df27
Fix TransposeElimination transformation (#24762)
### Details:
Handle the case when 2nd input of Transpose op is empty

### Tickets:
https://github.com/openvinotoolkit/openvino/pull/23950
2024-05-29 12:56:54 +00:00
Oleg Pipikin 8e0a646eed
Fix coverity 1544154 (#24753)
### Details:
 - Fix coverity 1544154

### Tickets:
 - CVS-140934
2024-05-29 12:21:29 +00:00
Sofya Balandina ae01c973d5
[ov conformance] Enable input range propagation via function (#23428)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-29 11:12:19 +00:00
Chenhu Wang feb0c7eff0
GN decomposition/tokenization test and snippets func test (#23903)
### Details:
 - *GroupNormalization decomposition test*
 - *GroupNormalization tokenization test*
 - *GroupNormalization snippets func test*

### Tickets:
 - *[CVS-136159](https://jira.devtools.intel.com/browse/CVS-136159)*
 - *[CVS-137359](https://jira.devtools.intel.com/browse/CVS-137359)*
2024-05-29 10:45:07 +00:00
Aleksandr Voron 4dfca61bd2
[CPU][ARM] Remove `acl_dw_convolution` from oneDNN (#24636)
This change was reverted by
https://github.com/openvinotoolkit/oneDNN/pull/230 because performance
degradation.

Degradation happens because ACL kernel was not selected due to
convolution check.
It was discussed with ACL team that this check could be removed and ACL
team removed this check in oneDNN.
Then I deleted this check in oneDNN fork:
https://github.com/openvinotoolkit/openvino/pull/24422

Since the check does not prevent us from selecting ACL kernel, we may
remove custom kernel again.

oneDNN PR: https://github.com/openvinotoolkit/oneDNN/pull/251

CVS-142130

TODO:
- [x] do performance check
2024-05-29 09:48:15 +00:00
Maciej Smyk 84cd71a71b
[DOCS] 2024.2 version update for master (#24746)
Docs version update to 2024.2
2024-05-29 09:04:29 +00:00
Mateusz Tabaka 229ce5839b
[NPU] Zero-initialize NpuInferProfiling::_dev_properties (#24758)
ze_device_properties_t has pNext pointer and if it's not nullptr then
it's assumed that it points to a different structure. pNext being
uninitialized can lead to a crash during zeDeviceGetProperties.
2024-05-29 08:52:04 +00:00
Roman Kazantsev 2ec64af350
[DOC][TF FE] Mark new operations for latest release (#24759)
**Details:** Mark new operations for latest release and unmark old ones.

**Ticket:** TBD

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-05-29 07:07:56 +00:00
duydl 3e3bea8985
[TF FE] Support AdjustSaturation operation (#24511)
### Details:
- Parse logic from
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/kernels/image/adjust_saturation_op.cc
to openVINO ops

### Tickets:
 - #24034

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-05-29 06:40:23 +00:00
Zhang Yi b66c43a11d
[CPU]Fix Qwen Rope Fusion (#24750)
### Details:
 - *Extend Qwen Rope Fusion*
- *PR to 2024.2 release
https://github.com/openvinotoolkit/openvino/pull/24727*
- *Migrate from original PR
https://github.com/openvinotoolkit/openvino/pull/24725*

### Tickets:
 - *CVS-142523*
2024-05-29 06:22:29 +00:00
Georgy Krivoruchko 60b2068c36
[TFLite] Fixed Densify reading implementation (#24707)
### Details:
 - Fixed Densify reading implementation
 - Added test for Densify
 - Added test for Dequantize
 - Removed unnecessary model test

### Tickets:
 - 127943

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-05-29 06:09:45 +00:00
Pratham Ingawale 4b7deb2366
[ONNX] Added support for Multinomial-7 operator (#23491)
### Details:
 - *Extend ONNX Frontend with Multinomial-7 operator*


### Tickets:
 - *118986*

---------

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Co-authored-by: Georgy Krivoruchko <georgy.krivoruchko@intel.com>
Co-authored-by: Piotr Krzemiński <piotrkrzeminski1234@gmail.com>
2024-05-29 06:08:56 +00:00
Kelvin Choi 485686dbbb
[GPU] Fix reshpae output padding (#24233)
### Details:
- *Update reshape's output padding by merging current padding and
input's padding*

### Tickets:
 - *137277*
2024-05-29 00:05:07 +00:00
Kelvin Choi cbeac47383
[GPU] Update loop inst ids instead of getting from prim (#24234)
### Details:
 - *Update loop inst ids instead of getting from prim*

### Tickets:
 - *137277*
2024-05-29 00:04:56 +00:00
Edward Shogulin 5f03621cfa
[TEST] Tensor comparation fix (#24735)
### Details:
 - *Tensor comparation fix*
2024-05-28 20:35:12 +00:00
Karol Blaszczak cc68c6f5e1
[DOCS] fix pytorch link (#24740) 2024-05-28 11:55:13 +00:00
Mircea-Aurelian Dan eededc2a3a
Update `CompiledModel` tests after `ov::model_name` prop was fixed (#24705)
### Details:
- *To align newly added behavior tests with other plugins,
`OVClassCompiledModelPropertiesDefaultTests` should not be tested with
`HETERO` device, as it is in `intel_cpu` plugin:
https://github.com/openvinotoolkit/openvino/blob/master/src/plugins/intel_cpu/tests/functional/shared_tests_instances/behavior/compiled_model/properties.cpp#L63-L67*

### Tickets:
 - *E-120273*
2024-05-28 11:15:54 +00:00
Andrei Kashchikhin 1fe36a26c8
[CI] [GHA] [DOCS] Add section on GPU (#24678)
### Tickets:
 - *140542*
2024-05-28 10:52:53 +00:00
Edward Shogulin 31fccc801f
[CPU] [ARM] JIT GELU Tanh (#23969)
### Details:
 - *[CPU] [ARM] jit gelu tanh*

### Tickets:
 - *CVS-138293*
2024-05-28 10:23:34 +00:00
Andrei Kashchikhin 38ce1fff0f
[CI] [GHA] Create cache directory recursively (#24732)
### Details:
 - Port of #24703
- The issue that was present on the release branches does not affect the
master branch yet but it could if, for example, a new folder is added to
the cache path.

### Tickets:
 - *142372*
2024-05-28 09:13:16 +00:00
Chenhu Wang 8265a986d5
[CPU] Reduce post ops as subgraph when output is not f32 precision (#24704)
### Details:
 - *reduce post ops only support f32 precision*

### Tickets:
 - *CVS-142322*
 
### PR for Release:
 - *https://github.com/openvinotoolkit/openvino/pull/24724*
2024-05-28 09:08:12 +00:00
Roman Lyamin 4dde282a95
[TRANSFORMATIONS][CPU] Move RoPE to common part (#24615)
### Details:
- *Transferring RoPE operation and transformations for subsequent reuse
in GPU plugin*
2024-05-28 08:20:37 +00:00
Andrzej Kopytko e2b8bf4fc7
DOCS Updated footer file (#24708)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-28 07:53:15 +00:00
Andrey Babushkin 0b349bffb5
Bigger runner for Windows Conditional Compilation build (#24718)
### Details:
This PR moves Windows Conditional Compilation build to a self-hosted
runner in Azure with 32 cores and 128 GB of RAM
2024-05-28 07:48:17 +00:00
Michal Miotk 63a13d4931
[GPU] fix for permute_f_y kernel (#24700)
### Details:
 - when tile_size < vector_size then JTIMES == 0

### Tickets:
 - 142398
2024-05-28 01:25:37 +00:00
Steve Yoo e6496dbbb8
[GPU] Enable Select 5d (#24544)
### Details:
 - *Enable select 5d in cl kernel*
 - *Added basic unit test for select 5d*

### Tickets:
 - *140122*
2024-05-28 01:11:23 +00:00
Ekaterina Aidova 4cf2ae0192
[PT FE]: fix segfault when resolving nested dict as model input (#24719)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-27 21:24:01 +00:00
Edward Shogulin 000b9f7058
[CPU] Exception handling: exception message logging (#24320)
### Details:
 - *Exception handling: exception message logging*

### Tickets:
- *NotSupported exception can have message, let's display it. For
example this ticket will be clear in this case: CVS-139934*
 - *Part of CVS-142409*
2024-05-27 19:37:08 +00:00
Anastasia Kuporosova 47415bcdf9
[PyOV] Hot-fix for hanging test (#24706)
### Details:
- During investigation I found out that it hangs in AUTO plugin but with
directly specified CPU plugin passes.

### Tickets:
 - CVS-141744
2024-05-27 15:03:42 +00:00
Ivan Tikhonov 0a1a233555
Fix MatMul SmartReshape in case of 1D input (#24701)
### Details:
Handled a case when "Other" input to MatMul is 1D


### Tickets:
 - *CVS-141638*
2024-05-27 14:24:22 +00:00
Karol Blaszczak c2c6fa7d1d
[DOCS] legal update and install fix (#24647) 2024-05-27 13:47:32 +00:00
Sergey Lyalin b0dfa6ac7f
PagedAttention Transformation: Rank alignment for replacements (#24690)
During the elimination of dependencies from `beam_idx` input and
`ReadValue`(s), we are replacing them by the new PA-related inputs and
sub-expressions dependent on other remaining inputs. In such
replacements we need to guarantee matching shape and element type of old
and new nodes. Before this PR it was not guaranteed for shape and
sometimes a scalar was replaced by a shape of rank 1 that led to errors
like `'start' input is not a scalar`. Now the shape is aligned.

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2024-05-27 16:58:02 +04:00
Jiangtao Hu 9ce97d1560
[DOCS] Fix broken url link and remove unnecessary step in Linux build env (#24494)
### Details:
 - *Fix broken url link*
 - *Remove unnecessary step in Linux build env*

### Tickets:
 - *N/A*
2024-05-27 12:00:05 +00:00
Piotr Kowalczyk 9732d4ac17
[GPU][ROIAlignRotated]: Fixed a bug with wrong batch indexing and added functional test for the op. (#24611)
This is a follow up to #23955

### Details:
 - Added functional test for ROI Align Rotated
- Fixed a "bug" with wrong batch index inside cl kernel revealed by
functional test for ROI Align Rotated.

### Tickets:
 - *[141877](https://jira.devtools.intel.com/browse/CVS-141877)*
2024-05-27 11:20:09 +00:00
Oleg Pipikin 94f287a051
Remove legacy test util func (#24659)
### Details:
 - Remove legacy test util func
 - *...*

### Tickets:
 - [CVS-128261](https://jira.devtools.intel.com/browse/CVS-128261)
2024-05-27 10:48:40 +00:00
Edward Shogulin 883211e483
[CPU] [ARM] JIT GELU Erf (#23948)
### Details:
 - *[CPU] [AARCH64] jit gelu erf*

### Tickets:
 - *CVS-138192*
2024-05-27 09:44:35 +00:00
Aleksandr Voron 438f4dca84
[CPU][ARM][DOC] Add swap note into Raspberry build procedure (#24679)
Add a note about swap according to the comment
https://github.com/openvinotoolkit/openvino/issues/24445#issuecomment-2116366405

---------

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2024-05-27 09:05:30 +00:00
KianYong Gan ebf43011d7
[NPU] Fix coverity issue (#24650)
### Details:
 - Coverity Fix as a line of the code is not reachable 
- Remove the line of dead code and add different log message for 3
different possible return

### Tickets:
 - E-125476
2024-05-27 07:45:44 +00:00
Jade Cho afc7b8e4c9
[GPU][LNL] Fix subgroup size issue of fc_imad_sa kernel (#24691)
LNL does not support 8 as subgroup size. It need to check before
compiling fc_imad shape agnostic kernel.

### Details:
- *Set subgroup size to 16 if simd8 is not supported in the target
device.*
2024-05-27 07:09:15 +00:00
Daniel 30d6e85505
[CPU] Inconsistent behavior/errors of Equal operation in comparison with TF framework (#24640)
Fix for TEST_DEVICE=CPU comparison of float16 infinite values

### Details:
- Introduced specialization for conversion float16->float32 in the CPU
plugin
 - xfail in layer tests is disabled for CPU device

### Tickets:
 - *24245*
2024-05-27 06:55:36 +00:00
Sergey Shlyapnikov dc523beb3e
[GPU] SDPA indirect inputs (#24665)
### Details:
 - Added indirect inputs support for SDPA kernel
 - Added setter for causal flag for ScaledDotProductAttention operation
- Added `ov::intel_gpu::hint::enable_sdpa_optimization` to
`ov::supported_properties` list
- Removed unused `TARGET_SEQ_LEN_BLOCK_SIZE > 1` check from kernel for
single token processing
 - Minor refactoring
- Added `OV_GPU_EnableSDPA` debug option (which allows to force SDPA
kernel for any ScaledDotProductAttention operation _(=1)_ / or
completely disable SDPA kernel _(=0)_, ignoring
`ov::intel_gpu::hint::enable_sdpa_optimization` property)

### Tickets:
 - *CVS-141213*
2024-05-27 06:11:37 +00:00
Roman Kazantsev af88a206eb
[OVC] Import openvino-tokenizers extensions from ovc tool (#24681)
**Details:** Previously, we were able to convert models requiring
openvino-tokenizers extensions (like with string operations, ragged
tensors) only in Python by `convert_model`. Now we add option to convert
using `ovc` tool. The tool internally imports extensions if they are
installed.

**Ticket:** TBD

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-05-26 15:40:40 +00:00
Roman Kazantsev 00a95994aa
Fix libhdf5.so not found error (#24689)
**Details:** Fix h5py so not found error

**Ticket:** TBD

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-05-26 15:40:14 +00:00
Ilya Lavrenov e91c8bc099
Removed deprecated cmake vars (#24687)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-25 23:40:34 +04:00
Ilya Lavrenov 72028b7bbc
Use CPU torch (#24658)
### Details:
- See
https://github.com/openvinotoolkit/openvino/actions/runs/9195359216/job/25292054679#step:16:224
2024-05-25 22:10:38 +04:00
Mustafa Cavus 0fe524bcbe
Unit test for dynamic expand fixed (#24684)
### Tickets:
 - CVS-142090
2024-05-25 16:37:08 +00:00
Nikolay Shchegolev 33c786cb2c
[CPU] smoke_/UndefinedEtSubgraphTest sporadic fail on SPR (#24680)
### Details:
- *To receive determined output of RandomUniform operation, need to set
`global_seed` or `op_seed`*

### Tickets:
 - *CVS-142075*
2024-05-24 20:46:51 +00:00
Sergey Lyalin 6de997ac4e
PagedAttention transformation supports K and V merged into a single tensor (#24655)
Enabled model: bigcode/starcoderbase-3b, bigcode/gpt_bigcode-santacoder.

There is a moderate refactoring in the code: move common code for
ReadValue-based pattern matching K, V and merged KV state management
into a single piece of code.
Extended UBR pattern for case when MQA doesn't have Reshape in the end
because KV cache is 3D instead of 4D and corresponding changes in the
detection of the number of KV heads.

In sync with https://github.com/ilya-lavrenov/openvino.genai/pull/20

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2024-05-24 20:20:27 +00:00
dependabot[bot] da360846ed
Update h5py requirement from <3.11.0,>=3.1.0 to >=3.1.0,<3.12.0 in /tests (#24358)
Updates the requirements on [h5py](https://github.com/h5py/h5py) to
permit the latest version.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="2c80981022"><code>2c80981</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2405">#2405</a> from
takluyver/rever-3.11</li>
<li><a
href="76afe10048"><code>76afe10</code></a>
Add HDF5 1.14.4 fixes to release notes</li>
<li><a
href="009047936d"><code>0090479</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2406">#2406</a> from
ajelenak/libhdf5-1.14.4</li>
<li><a
href="0f071a4d64"><code>0f071a4</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2407">#2407</a> from
h5py/dependabot/github_actions/actions-45223d3826</li>
<li><a
href="944a4a6967"><code>944a4a6</code></a>
Bump peaceiris/actions-gh-pages from 3 to 4 in the actions group</li>
<li><a
href="8f513ced5e"><code>8f513ce</code></a>
Clean up release notes</li>
<li><a
href="62bd813202"><code>62bd813</code></a>
Rename new whatsnew file, add to index</li>
<li><a
href="9c305e23ce"><code>9c305e2</code></a>
Updated CHANGELOG for 3.11.0</li>
<li><a
href="9e107c4a78"><code>9e107c4</code></a>
bumped version to 3.11.0</li>
<li><a
href="71af64dec8"><code>71af64d</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2360">#2360</a> from
loichuder/visit-links</li>
<li>Additional commits viewable in <a
href="https://github.com/h5py/h5py/compare/3.1.0...3.11.0">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2024-05-24 20:17:47 +00:00
Alina Kladieva 66093834e3
Bump product version to 2024.3 (#24673) 2024-05-24 14:59:20 +02:00
hyunback kim 8682e5e4c9
[GPU] Update oneDNN v3.5 (#24663)
Applied oneDNN convolution improvement in Stable-Diffusion LNL.

### Tickets:
 - *ticket-id*

Signed-off-by: hyunback <hyunback.kim@intel.com>
2024-05-24 10:29:44 +00:00
Egor Duplenskii 0297faca9f
[CPU] Avoid extra processing of the sync nodes in scope of Infer call (#24227)
### Details:
 - To reduce Infer overhead
 - The new flow is:
   1) Define sync points from all the nodes perspective.
   2) Use sync points in scope of Allocate
3) Define executable sync points from overall sync points but
considering only executable nodes.
4) Keep executable sync points ordered to avoid additional logic in
scope of Infer call.

### Tickets:
 - *ticket-id*
2024-05-24 10:00:45 +00:00
Vladislav Golubev cfb05bf7e3
[Snippets] Test infrastructure for lowered passes (#24152)
### Details:
 - *Extended LIR interface to make LIR creation from scratch possible*
 - *Introduced `LoweredPassTestsF` base class for LIR comparison*
- *Added some helpers for easier LIR creation from scratch (not from
`ov::Model`)*
- *Introduced `LIRComparator` class. For LIR related things comparison,
a custom comparators were written. For `ov::Node` comparison, the
existing comparator from `GraphComparator` class is used.*
- *Added a test case for `InsertLoadStore` pass: as an example of a
simple LIR comparison (only expressions + `ov::Node` comparison is
necessary to fully cover the pass code)*. The pass was not fully
covered.
- *Added test cases for `BrgemmBlocking` cpu lowered pass: as an example
of complicated LIR comparison, where `LoopManager` and descriptors
comparison are also necessary. This pass was fully covered.*

### Tickets:
 - *CVS-139926*
2024-05-24 09:58:14 +00:00
Sebastian Golebiewski 87631e33d1
[DOCS] Update notebooks for master (#24669)
Updating `Interactive Tutorials` section with new content
2024-05-24 09:13:26 +00:00
Andrei Kashchikhin cb85ddcb46
[CI] [GHA] Fix GPU job display name if the job is skipped (#23965)
### Details:
 - If the GPU job is skipped, the UI shows:

![image](https://github.com/openvinotoolkit/openvino/assets/65596953/6c8c8142-d12e-4f80-a2c3-ab17ff9e3b1f)

The jobs created by `matrix` will have the necessary distinguishable
properties in the `()` after the job name, e.g., for `Conformance`:

![image](https://github.com/openvinotoolkit/openvino/assets/65596953/d9104eda-3c33-4cee-ab33-4df0e41cc6f3)
so we do not need `matrix`.
2024-05-24 09:08:52 +00:00
Ivan Tikhonov 17f8e86e5f
ConcatToBroadcast transformation (#24661)
Details:

Due to the issue in the e2e test in
https://github.com/openvinotoolkit/openvino/pull/24597 we decided to
exclude Concat to Tile conversion from the transformation. It will be
covered in another ticket.

- Add a ConcatToBroadcast transformation to replace Concat having inputs
from the same output with a Broadcast
- Add a test for the ConcatToBroadcast transformation


Significantly reduce model compile time and performance time.

Tickets:
[CVS-138829](https://jira.devtools.intel.com/browse/CVS-138829),
[CVS-138077](https://jira.devtools.intel.com/browse/CVS-138077)

---------

Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>
Co-authored-by: Andrii Staikov <andrii.staikov@intel.com>
2024-05-24 07:33:00 +00:00
Pavel Esir 2a9eadf991
clamp int32 -> float16 Convert::evaluate (#24653)
Details:

- enable clamping of int32 values when converted to fp16 the same way we
do when compress constant from f32->f16

Tickets:
CVS-141762
2024-05-24 05:00:14 +00:00
Wilson Seok 3eb8d55f08
[GPU] Workaround in convolution ocl impl for fp32 output hack of avgpool when u8/i8 input (#24643)
Convolution which has u8 AvgPool layer as input0 is handled as quantized
in transformation and it has zp constants in transformed graph. But gpu
plugin has changed AvgPool output data type to fp32 due to accuracy
issue. The change causes convolution ocl impl doesn't recognize
quantized convolution.

### Details:
- Add Workaround in convolution ocl impl for fp32 output hack of avgpool
when u8/i8 input

### Tickets:
 - 141396
2024-05-24 00:24:35 +00:00
Ilya Lavrenov e2b646f91e
Simplify cmake check for Ninja multi-config (#24651)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-24 00:08:08 +00:00
Ilya Lavrenov 3ca4919219
Set _GLIBCXX_USE_CXX11_ABI globally in OV cmake (#24657)
### Details:
- It can be useful when other targets within user project need to be
linked with _GLIBCXX_USE_CXX11_ABI=0
2024-05-23 20:33:10 +00:00
Andrei Kashchikhin f028ecf0f7
[CI] [GHA] Investigate and mitigate Mac workflows (#24631)
### Tickets:
 - *142049*
2024-05-23 19:58:53 +00:00
Vladislav Denisov 8d99a63f6d
[GoodFirstIssue][OP CONFORMANCE][TEMPLATE] Added static shape generator for dynamic shapes (#24125)
### Details:
 - Added generator of static shapes based on an operation type.

### Tickets:
 - https://github.com/openvinotoolkit/openvino/issues/23551
2024-05-23 17:59:34 +00:00
Wang Wangwang 80237bf292
Revert "[DOCS] Update the document of HETERO pipeline parallelism" (#24644)
This reverts commit 03aad66230.

### Details:
Revert the commit because there are some models with stateful OPS
(assign/readvalue) not in same attention node, hetero pipeline
parallelism does not work.

### Tickets:
 - *CVS-141771*
2024-05-23 13:45:38 +00:00
Ilya Lavrenov fc6af4f4af
Use system TBB by default for Deb, RPM (#24613)
### Details:
 - Otherwise, currently users have error during Debian package build
2024-05-23 12:40:05 +00:00
Michal Miotk f2fdb4bd1d
[GPU] fix for mixing types in permute_f_y (#24648)
### Details:
 - fix mixing IN and OUT vec type

### Tickets:
 - 140728
2024-05-23 11:49:27 +00:00
Yuan Hu 1a4ae5e7a3
[core] fix thread safe issue in #19832 (#24562)
### Details:
- *I lost code `t_stream_count_map[(void*)this] = item.first;` in
#19832*
 - *the thread safe issue happen in below workflow*
 - create thread A
call CustomThreadLocal:local() in thread A -> create stream A (the count
of stream A is 2)
   destory thread A (the count of stream A is 1)
   create thread B (same thread id with thread A)
call CustomThreadLocal:local() in thread B -> use stream A(the count of
stream A is 1, so it's broken)
- *add testcase, also fix
https://github.com/openvinotoolkit/openvino/pull/19986/files#r1332774754*

### Tickets:
 - Closes https://github.com/openvinotoolkit/openvino/issues/24509

---------

Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
2024-05-23 11:47:57 +00:00
Mircea-Aurelian Dan c0853f0f2f
Upstream NPU behavior tests (#24552)
### Details:
- By this PR we want to create `ov_npu_func_tests` executable having
functional tests from `NPU plugin` (SLTs and Subgraphs to be added
later).
- Functional tests were copy-pasted to <code><a
href="https://github.com/openvinotoolkit/openvino/compare/master...MirceaDan99:openvino:EISW-120273/original/copy_npu_func_tests_to_ov">EISW-120273/original/copy_npu_func_tests_to_ov</a></code>
branch to review changes easier at:
d4f0300e1b..7b7e177f11
- Latest validation is:
https://vpux-ci-vpuip.ir.intel.com/job/ov_integration/job/ov_integration/1167/

### Tickets:
 - *E-120273*
2024-05-23 11:28:53 +00:00
Mustafa Cavus 4b8641ee3f
Added quantized_decomposed quantization unit tests (#24388)
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
Co-authored-by: Surya Siddharth Pemmaraju <surya.siddharth.pemmaraju@intel.com>
Co-authored-by: Yamini Nimmagadda <yamini.nimmagadda@intel.com>
2024-05-23 10:15:11 +00:00
Tatiana Savina f9c039418c
[DOCS] Direct to Python tab in the ovc transition guide (#24624)
### Details:
 - *item1*
 - *...*

### Tickets:
 - 140454
2024-05-23 09:20:04 +00:00
Alicja Miloszewska 16005894f9
[OV JS] Add method descriptions of CompiledModel (#24571)
### Details:
 - Add method descriptions to *lib/addon.ts* 

### Tickets:
 - *141291*

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-23 08:25:03 +00:00
Przemyslaw Wysocki c4f33cec55
[PyOV] Extend Python API with `Col2Im-15` (#24569)
### Details:
 - Add Python API for `Col2Im-15`
- Requires https://github.com/openvinotoolkit/openvino/pull/24548 to
work and pass CI

### Tickets:
 - CVS-138920

### Related PRs:
- https://github.com/openvinotoolkit/openvino/pull/24548
- https://github.com/openvinotoolkit/openvino/pull/24197
- https://github.com/openvinotoolkit/openvino/pull/23947

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-23 07:51:22 +00:00
Ilya Lavrenov 3bbb35cea6
Revert "[PyOV] Reenable test_cancel" (#24639)
Reverts openvinotoolkit/openvino#24590

Sporadically fails
https://github.com/openvinotoolkit/openvino/actions/runs/9189693102/job/25273009310

Looks like tests relies on certain execution time of model inference,
while it depends on machine
2024-05-23 07:41:09 +00:00
Vladimir Paramuzov 23d487bdfb
[GPU] Allow signed int8 for WOQ (#24620)
### Details:
 - Add i8 data type to list of supported dequantization types for woq

### Tickets:
 - *CVS-131044*
2024-05-23 07:07:09 +00:00
Tomasz Jankowski 9ec1c4a1fe
[Tmpl test] Preprocess: Drop legacy comparison (#24622)
### Details:
 - Fixed tensors' shapes.

### Tickets:
 - CVS-137216
2024-05-23 06:39:43 +00:00
awayzjj d0e6f8ffea
Implement CPU plugin just-in-time emitter for Mod operation (#24574)
Closes https://github.com/openvinotoolkit/openvino/issues/24061
### Details:
 - Mod operation

### Tickets:
 - [CVS-137689](https://jira.devtools.intel.com/browse/CVS-137689)
2024-05-23 06:24:18 +00:00
Attila Csok 00ef5c9a07
[intel-npu] removing cpu_pinning string from CID command string (#24566)
### Details:
- removing ENABLE_CPU_PINNING from command string passed to CiD, for
older compiler versions to enable backwards compatibility

### Tickets:
 - EISW-124233
2024-05-23 06:05:46 +00:00
Inbasekaran Perumal 9025003860
Align behavior of ONNX Frontend function ReduceSumSquare-11, 13, 18 with original framework (#23798)
Hello maintainers,

Since my previous PR
(https://github.com/openvinotoolkit/openvino/pull/22993#issue-2146681772)
had diverged significantly from the master branch, and also included
additional changes, I thought it would be best to create a new PR.
@gkrivor, could you please take a look?

This closes
https://github.com/openvinotoolkit/openvino/issues/20563#issue-1949590592.

---------

Co-authored-by: Georgy Krivoruchko <georgy.krivoruchko@intel.com>
2024-05-23 03:39:30 +00:00
Wang, Yang c904b8e182
[AUTO] Load cached model to target device W/O CPU accelerating (#24618)
### Details:
- update logic of only loading cached model to GPU with AUTO if GPU
cached blob exists and `ov::intel_auto::enable_startup_fallback` is
enable

### Tickets:
 - CVS-138574
2024-05-23 02:02:46 +00:00
Andrew Kwangwoong Park 4b0868c98a
[GPU] Apply dynamic padding for onednn gemm (#24605)
### Details:
 - Apply dynamic padding for onednn gemm
 - Update memory descriptor to handle the padded dims and strides

### Tickets:
 - 140516

---------

Signed-off-by: Andrew Park <andrew.park@intel.com>
2024-05-22 21:06:26 +00:00
Ilya Lavrenov 50b731639a
Added -Wno-stringop-overflow for GPU unit tests as well (#24638)
### Details:
- The same https://github.com/openvinotoolkit/openvino/pull/24628 for
GPU Unit tests
2024-05-22 20:35:41 +00:00
Andrei Kashchikhin 8c5b357135
[CI] [GHA] Add Dockerfile for U20 and use it in the `Build` job in Linux workflow (#24573)
### Tickets:
 - *141573*
2024-05-22 18:27:43 +00:00
Andrzej Kopytko ef6ca0a13d
[Docs] Page styling (#24637)
another part
2024-05-22 18:27:22 +00:00
Tomasz Jankowski 6f7cf28847
[Tmpl test] ExperimentalDetectronPriorGridGenerator: Drop legacy comparison (#24592)
### Details:
- Removed 'actual comparison size' parameter from base template test
class `CommonReferenceTest`.
- Moved partial comparison logic to
`ReferenceExperimentalPGGLayerTest::Validate()` - it's needed only in
this test.

### Tickets:
 - CVS-137159
2024-05-22 17:17:04 +00:00
Vladislav Golubev 0eab4efffa
[CPU] Avoid overflow in GatherDecompression builders, enable tests (#24629) 2024-05-22 15:40:52 +00:00
Alina Kladieva b014776bf4
[GHA] Checkout the latest OneDNN for GPU in nightly (#24534)
### Tickets:
 - CVS-139627
2024-05-22 14:57:06 +00:00
Luo Cheng f400fe5d87
[CPU] Fix segment fault for PagedAttention when head size is multiple of 16 (#24627)
### Details:
- *Fix segment fault for PagedAttention when head size is multiple of
16*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-22 14:49:39 +00:00
Mustafa Cavus 87f25aa14b
Torchfx dynamic shapes initial (CVS-139182) (#24578)
### Details:
 - Enabling dynamic shapes with aot_autograd

### Tickets:
 - CVS-139182

---------

Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>
2024-05-22 14:04:16 +00:00
Maciej Smyk 0cd4710321
[DOCS] Assets move - images for master (#24621)
Jira: 138084

Moving image assets closer to the source files.
2024-05-22 14:00:50 +00:00
Katarzyna Mitrus 00856cdcb2
[Op][Internal] Reference implementation for internal::RMS op (#24556)
### Details:
- Reference implementation and ref tests for
[internal::RMS](70142121c1/src/common/transformations/include/ov_ops/rms.hpp)
(moved from gpu custom ops) available for common transformations
 - Enable Accuracy tests for RMSFusion transformation
 
 The changes moving RMS from gpu to internal are from PR:
 -  #24539 (to be merged first)
 
 Internal RMS op docs:
- https://github.com/openvinotoolkit/openvino/pull/24564

 ### Tickets:
 - Related to 136262

---------

Co-authored-by: michal-miotk <michal.miotk@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-22 13:32:47 +00:00
Daniil Lyakhov 58e6ba6a85
PyTorch QAT to PTQ documentation update (#24363)
### Details:
QAT documentation for NNCF Torch and NNCF Tensorflow is spitted on two
pages

* quantization-aware-training-pytorch.rst is QAT by `nncf.quantize`
method documentation
* quantization-aware-training-tensorflow.rst file is a copy of original
quantization-aware-training.rst without the PyTorch part

Link to generated doc:

http://openvino-doc.iotg.sclab.intel.com/nncf-docs/openvino-workflow/model-optimization-guide/compressing-models-during-training.html


### Tickets:
 - 129586

---------

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2024-05-22 13:22:55 +00:00
Luwei Zhou 0bac4612da
[CPU]Align dump_check.py with blob dump header precision switch from deprecated ePrecision to ov::element::Type_t. (#24617)
66a8600564 switched precision field in
dump header from ePrecision to ov::element::Type_t. update dump_check.py
to parse precision correctly.
2024-05-22 13:19:07 +00:00
Katarzyna Mitrus 0a5a369efa
[Op] ROIAlignRotated version alignment from opset14 to opset15 (#24585)
### Details:
- ROIAlignRotated as added within 2024.2, should be moved to the latest
opset15


### Tickets:
 - 141682
2024-05-22 13:06:06 +00:00
Damian Kurek da168d2bd7
[GPU] Remove link-time stringop overflow warning (#24628)
Remove stringop overflow warning as a temporal workaround for oneDNN
warning issue, which caused compilation issues on Ubuntu 24.04 (GCC 13 +
LTO)

### Details:
 - Remove warning from intel-gpu link flag properties

### Tickets:
 - CVS-141874
2024-05-22 12:53:59 +00:00
Jan Iwaszkiewicz 4031e791bc
[PyOV] Refactor dtype to type conversion (#24626)
### Details:
- Continuation of https://github.com/openvinotoolkit/openvino/pull/24588
- Initialized "int-to-type" map with more clear "string-to-type" map
first, using `num()` value from constructed dtypes.

### Tickets:
 - *...*
2024-05-22 12:38:12 +00:00
KianYong Gan 5a32c49f97
[NPU] Fix issue model name not return from meta-data (#24529)
### Details:
A new test case added in openvino
fd9a63cffd/src/tests/functional/plugin/shared/src/behavior/compiled_model/properties.cpp (L240)
but it encounter some issue in CID path where the model_name return is
null, this PR trying to solve the issue

### Tickets:
 - *EISW-121043*
2024-05-22 12:15:14 +00:00
Sergey Shlyapnikov 1e5f025bdd
[GPU] Add initial SDPA implementation (#24466)
### Details:
- Add initial SDPA implementation, input transpose fusions and GQA
related optimization (broadcast fusion)
2024-05-22 11:54:27 +00:00
KianYong Gan 710568bd58
[NPU] Add logger in src/plugins/intel_npu/src/backend/ (#24019)
[NPU] Add logger in src/plugins/intel_npu/src/backend/ to Increase
verbosity of errors returned

### Details:
 Improve log and debug message
 - src/plugins/intel_npu/src/backend/include/zero_backend.hpp
 - src/plugins/intel_npu/src/backend/src/zero_backend.cpp
 - src/plugins/intel_npu/src/backend/src/zero_device.cpp
 - src/plugins/intel_npu/src/backend/src/zero_executor.cpp
 - src/plugins/intel_npu/src/backend/src/zero_infer_request.cpp
 - src/plugins/intel_npu/src/backend/src/zero_init.cpp
 - src/plugins/intel_npu/src/backend/src/zero_pipeline.cpp

### Tickets:
 - *ticket-id*
2024-05-22 11:28:41 +00:00
River Li 0d95325972
[C API] fix element type mismatch issue (#24608)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-22 09:21:45 +00:00
Sebastian Golebiewski 09c05f12a0
[DOCS] Limitation of BF16 inference precision for LLMs (#24501)
Creating `Limitation of the bf16 inference precision` section to
describe an issue of higher accuracy loss than the pre-determined
threshold of 0.5% and present possible solutions.
This PR addresses JIRA ticket: 138832.
2024-05-22 08:45:26 +00:00
Stefania Hergane 63e043bf00
Extend network precision with `u4`, `i4` for L0 backend (#24432)
### Details:
 - *Update `zero_infer_request.cpp` with `u4` and `i4`* for intel_npu.
 - *...*

### Tickets:
 - *E#121561*
2024-05-22 08:04:57 +00:00
Surya Siddharth Pemmaraju e7c60bb18a
Fixed bug with inlined inputs (#24448)
### Details:
- Fixed bug with inlined inputs for fx decoder which were being added as
parameters and are not needed.

### Tickets:
 - (https://jira.devtools.intel.com/browse/CVS-116702)

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2024-05-22 07:29:36 +00:00
hyunback kim 7f4e76694b
[GPU] gemm_tile supports block read when leftover with 4byte-size align in dynamic. (#24535)
* Use block read in 4byte aligned left-over case. Static was already
used (https://github.com/openvinotoolkit/openvino/pull/23400) This PR
will apply in dynamic.



### Tickets:
 - *141032*

---------

Signed-off-by: hyunback <hyunback.kim@intel.com>
2024-05-22 07:24:13 +00:00
Mustafa Cavus 19fd28b433
Torchfx gptq pattern replacer (#23700)
Required for GPTQ int4 LLMs. (ChatGLM2, ChatGLM3, Llama2)
Includes the transformations below:
- GPTQ Decompression pattern replacer


![image](https://github.com/openvinotoolkit/openvino/assets/59713154/d68ad0c9-473c-4590-a8fe-e62171b72ab7)


- GPTQ Multiplication pattern replacer


![image](https://github.com/openvinotoolkit/openvino/assets/59713154/954b2f1e-b79c-4eed-b5f8-77d56cd776a9)

Ticket: CVS-139181

---------

Co-authored-by: Surya Siddharth Pemmaraju <surya.siddharth.pemmaraju@intel.com>
2024-05-22 05:55:43 +00:00
Aleksandr Voron a1b9b144ef
[CPU][ARM] Enable NHWC Pooling (#24492)
PR has to be merge after
https://github.com/openvinotoolkit/openvino/pull/24491 since ACL 24.04
contains needed fix for Pooling.
CVS-130054
2024-05-22 05:54:20 +00:00
Tingqian Li d8f5d7bdd3
[CPU] Support weight-compression dt s8 (#24457)
### Details:
- FC with symmetrically quantized/compressed weight may have i8 (instead
of u8) as weight data type (it saves the zero-point subtraction cost),
this change added support to such weight dt.
 - oneDNN fork PR: https://github.com/openvinotoolkit/oneDNN/pull/249

### Tickets:
 - *CVS-131042*
2024-05-22 05:37:03 +00:00
Vishniakov Nikolai 16e8db8023
[OV JS] Electron compatibility (#24558)
### Details:
- Fix Electron compatibility on Windows by specifying flag:
`CMAKE_SHARED_LINKER_FLAGS="/DELAYLOAD:NODE.EXE"`

### Tickets:
 - 141536

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-22 05:36:44 +00:00
dependabot[bot] c744950582
Update h5py requirement from <3.11.0,>=3.1.0 to >=3.1.0,<3.12.0 in /src/bindings/python (#24413)
Updates the requirements on [h5py](https://github.com/h5py/h5py) to
permit the latest version.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="2c80981022"><code>2c80981</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2405">#2405</a> from
takluyver/rever-3.11</li>
<li><a
href="76afe10048"><code>76afe10</code></a>
Add HDF5 1.14.4 fixes to release notes</li>
<li><a
href="009047936d"><code>0090479</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2406">#2406</a> from
ajelenak/libhdf5-1.14.4</li>
<li><a
href="0f071a4d64"><code>0f071a4</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2407">#2407</a> from
h5py/dependabot/github_actions/actions-45223d3826</li>
<li><a
href="944a4a6967"><code>944a4a6</code></a>
Bump peaceiris/actions-gh-pages from 3 to 4 in the actions group</li>
<li><a
href="8f513ced5e"><code>8f513ce</code></a>
Clean up release notes</li>
<li><a
href="62bd813202"><code>62bd813</code></a>
Rename new whatsnew file, add to index</li>
<li><a
href="9c305e23ce"><code>9c305e2</code></a>
Updated CHANGELOG for 3.11.0</li>
<li><a
href="9e107c4a78"><code>9e107c4</code></a>
bumped version to 3.11.0</li>
<li><a
href="71af64dec8"><code>71af64d</code></a>
Merge pull request <a
href="https://redirect.github.com/h5py/h5py/issues/2360">#2360</a> from
loichuder/visit-links</li>
<li>Additional commits viewable in <a
href="https://github.com/h5py/h5py/compare/3.1.0...3.11.0">compare
view</a></li>
</ul>
</details>
<br />


Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2024-05-22 00:11:31 +00:00
Asthestarsfalll afc3aac267
【Hackathon 6th No.43】add paddle tril_triu (#23982)
### Details:
add paddle tril and triu

### Reference
Code:
https://github.com/PaddlePaddle/Paddle/blob/release/2.6/python/paddle/tensor/creation.py#L1431
Support data type: int32, int64, float32, float64, float16, complex64,
complex128 (openvino do not support float64, float16, complex64
complex128)

### Python simulation code
```python
import paddle

a = paddle.randn((3, 4))


def func(x, diagonal=0, mode='triu'):
    h, w = x.shape
    horizontal_range = paddle.arange(0, w)
    horizontal_range = paddle.unsqueeze(horizontal_range, 0)
    vertical_range = paddle.arange(0, h)
    vertical_range = paddle.unsqueeze(vertical_range, 1)
    if diagonal != 0:
        vertical_range += diagonal
    if mode == 'triu':
        mask = horizontal_range >= vertical_range
    else:
        mask = horizontal_range <= vertical_range
    print(mask)
    return paddle.where(mask, x, paddle.zeros_like(x))


def tril(x, diagonal=0):
    return func(x, diagonal, 'tril')

def triu(x, diagonal=0):
    return func(x, diagonal, 'triu')



b = paddle.tril(a, -1)
c = tril(a, -1)
print(b)
print(c)
print((b==c).mean())

```

### Test


![240411_19h35m47s_screenshot](https://github.com/openvinotoolkit/openvino/assets/72954905/735e1fa0-cd5f-4b56-b7fd-388b95eb1177)


waiting for:
- https://github.com/openvinotoolkit/openvino/pull/23010

---------

Co-authored-by: mei, yang <yang.mei@intel.com>
2024-05-21 19:09:20 +00:00
Przemyslaw Wysocki fba3ec0d47
[Op] `Col2Im-15` reference implementation (#24548)
### Details:
- Similar in functionality to
https://pytorch.org/docs/stable/generated/torch.nn.Fold.html, Col2Im is
`torch.nn.Fold` restricted to two output spatial dimensions

### Tickets:
 - CVS-138919

### Related PRs:
- https://github.com/openvinotoolkit/openvino/pull/24197
- https://github.com/openvinotoolkit/openvino/pull/23947
- https://github.com/openvinotoolkit/openvino/pull/24569

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-21 18:46:35 +00:00
Sergey Lyalin 1aa2e178d0
PagedAttention transfomration: SDPA with scale input and implicitly broadcasted KV cache (#24596)
Extended model support in PagedAttention transformation:
 - SDPA with `scale` input
- Case when KV inputs into SDPA are implicitly broadcasted by 2nd
dimension.
- More accurate application of PrevSequenceLengthPattern that now can
track batch dimension as well.

Enables tiiuae/falcon-7b and BAAI/AquilaChat2-7B.

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2024-05-21 18:41:09 +00:00
Vladislav Golubev c17ea55cac
[Snippets] Ubuntu 24.0 build fix (#24612)
### Tickets:
 - *CVS-141872*
2024-05-21 17:13:58 +00:00
Vladislav Golubev 222ba2e585
[Snippets] TPP build fix (#24610) 2024-05-21 16:35:24 +00:00
Sofya Balandina ba6681ee15
Fix some case with overflow data in fill_data_random (#24418)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-21 16:27:31 +00:00
Jan Iwaszkiewicz 0c65b35bb8
[PyOV] Optimize dtype to Type conversion (#24588)
### Details:
- Remove costly conversion to string by replacing it with unique ids of
each dtype.
- More on `dtype.num`:
https://numpy.org/devdocs/reference/generated/numpy.dtype.num.html#numpy.dtype.num

### Tickets:
 - *...*
2024-05-21 15:50:04 +00:00
oogee c76b5f2776
Use shell parameter expansion to make getting source path work in non-bash shells (#24598)
Currently `BASH_SOURCE[0]` was used, which is only available on bash.

I changed it to `${BASH_SOURCE:-$0}` which is supported by at least
bash, zsh and dash, as explained by
[https://stackoverflow.com/a/68359914/9028340](https://stackoverflow.com/a/68359914/9028340)

It uses shell parameter expansion

https://www.gnu.org/software/bash/manual/html_node/Shell-Parameter-Expansion.html

https://zsh.sourceforge.io/Doc/Release/Expansion.html#Parameter-Expansion

Addresses #17392
2024-05-21 15:28:52 +00:00
Sofya Balandina 76d3410a7c
[template] Fix debug build for linux (#24490)
### Tickets:
 - *[CVS-138757](https://jira.devtools.intel.com/browse/CVS-138757)*
2024-05-21 15:23:42 +00:00
Evgenya Nugmanova ffc77d0bcc
WA for pass::Manager bug (#24604)
### Details:
 - *WA for pass::Manager bug*

### Tickets:
 - temporary workarounds CVS-141764
2024-05-21 14:56:07 +00:00
Katarzyna Mitrus b71eab2555
[Spec][Internal][Op] Specification for RMS internal op (#24564)
### Details:
- Dev documentation for the existing
[internal::RMS](70142121c1/src/common/transformations/include/ov_ops/rms.hpp)
op
(specified as is without any additional features, to be developed and
updated if needed)
- RMS was created initially as a [custom gpu
RMS](9fadb5ac64/src/plugins/intel_gpu/include/intel_gpu/op/rms.hpp)
operation, and it's going to be moved to op::internal::RMS to be
available for common transformations
- Similar approach as it was done for AUGRUCell/AUGRUSeqence, so the
place for such documents has been already agreed and it's not a part of
the official web docs tree
 
### Tickets:
 - 134914, dicsussion 129027
2024-05-21 14:20:35 +00:00
Sergey Shlyapnikov 248c841e85
[GPU] Fix U8 weights identification as a quantization case (#24488)
### Details:
- Fix the issue where `conv_params.quantization` was not correctly
identified as a quantization case when using U8 weights data (which is
allowed by ConvertConvolutionToInternal transformation pass)

### Tickets:
 - 139740
2024-05-21 12:10:27 +00:00
Sonder 24137ffdfc
【Hackathon 6th No.44】add paddle rsqrt (#23985)
Add `paddle.rsqrt` op for openvino

paddle.rsqrt(x, name=None)

The rsqrt activation function.

The calculation formula is as follows:

$$
out=\frac{1}{\sqrt{x}}
$$


![image](https://github.com/openvinotoolkit/openvino/assets/55493212/b197c068-96f8-47f4-8d48-913ee93d01a9)

Waiting for:
- https://github.com/openvinotoolkit/openvino/pull/23010

---------

Co-authored-by: mei, yang <yang.mei@intel.com>
2024-05-21 10:20:29 +00:00
Keyon Jie 90139c2b81
[TFL FE]: gelu: fix issue when approximate is not specified (#24356)
Sometimes the approximate attribute is not specified in the .tflite
file, we need to check its availability before retriving it, otherwise
we might hit the 'Check 'opts != nullptr' failed' failure with calling
get_attribute() directly.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
2024-05-21 10:03:20 +00:00
Maksim Kutakov 1007de55fd
[CPU] Support nested internal states (#24247)
### Details:
This patch contains all the necessary changes to support internal states
in the composite nodes (i.e. If, Loop, TensorIterator operations). Main
changes:
1. Move the internal states registry to the graph context, so that all
the nested internal states become accessible on the infer request level.
2. Move the state assing/commit actions to the node execute level, so
that Loop and TensorIterator ops are automatically supported.

### Tickets:
 - CVS-134470
2024-05-21 09:33:55 +00:00
Mateusz Mikolajczyk 23b54736e4
[Opset15] Implementation for EmbeddingBagPacked and EmbeddingBagOffsets ops (#24541)
### Details:
- *Create PoC implementation for EmbeddingBag Offsets and Packed that
introduce mode 'mean'*
 - *Add Core, Reference and CPU implementation for both ops*

Specification will be added in separate PR

### Tickets:
 - *138229*

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-21 09:07:14 +00:00
Vladislav Golubev 6556567bdd
[Snippets] Extract BrgemmCopyB from M blocking if there are no KN blocking (#24551)
### Details:
- *Extract BrgemmCopyB from M blocking if there are no KN blocking
loops*
 - *Tests will be added after #24152 merge*

### Tickets:
 - *CVS-140751*
2024-05-21 09:06:58 +00:00
Gorokhov Dmitriy b745b23599
[CPU] Merge bf16 weights type conversion with repack stage (#24595)
### Details:
- This PR extends existing weights type conversion + repack optimization
for bf16 precision. This change is needed to minimize memory footprint
on model compilation stage for models with BF16 compressed weights.
2024-05-21 09:05:16 +00:00
barnasm1 d9b0b69871
[CORE] Test opset1::Concat shape inference with op reuse (#24383)
### Details:
 - Add new tests to cover case with reuse of pre-created operator

### Tickets:

 - *[CVS-94507](https://jira.devtools.intel.com/browse/CVS-94507)*
2024-05-21 08:22:33 +00:00
dependabot[bot] fd9a63cffd
Bump requests from 2.31.0 to 2.32.0 in /docs (#24600)
Bumps [requests](https://github.com/psf/requests) from 2.31.0 to 2.32.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/psf/requests/releases">requests's
releases</a>.</em></p>
<blockquote>
<h2>v2.32.0</h2>
<h2>2.32.0 (2024-05-20)</h2>
<h2>🐍 PYCON US 2024 EDITION 🐍</h2>
<p><strong>Security</strong></p>
<ul>
<li>Fixed an issue where setting <code>verify=False</code> on the first
request from a
Session will cause subsequent requests to the <em>same origin</em> to
also ignore
cert verification, regardless of the value of <code>verify</code>.
(<a
href="https://github.com/psf/requests/security/advisories/GHSA-9wx4-h78v-vm56">https://github.com/psf/requests/security/advisories/GHSA-9wx4-h78v-vm56</a>)</li>
</ul>
<p><strong>Improvements</strong></p>
<ul>
<li><code>verify=True</code> now reuses a global SSLContext which should
improve
request time variance between first and subsequent requests. It should
also minimize certificate load time on Windows systems when using a
Python
version built with OpenSSL 3.x. (<a
href="https://redirect.github.com/psf/requests/issues/6667">#6667</a>)</li>
<li>Requests now supports optional use of character detection
(<code>chardet</code> or <code>charset_normalizer</code>) when
repackaged or vendored.
This enables <code>pip</code> and other projects to minimize their
vendoring
surface area. The <code>Response.text()</code> and
<code>apparent_encoding</code> APIs
will default to <code>utf-8</code> if neither library is present. (<a
href="https://redirect.github.com/psf/requests/issues/6702">#6702</a>)</li>
</ul>
<p><strong>Bugfixes</strong></p>
<ul>
<li>Fixed bug in length detection where emoji length was incorrectly
calculated in the request content-length. (<a
href="https://redirect.github.com/psf/requests/issues/6589">#6589</a>)</li>
<li>Fixed deserialization bug in JSONDecodeError. (<a
href="https://redirect.github.com/psf/requests/issues/6629">#6629</a>)</li>
<li>Fixed bug where an extra leading <code>/</code> (path separator)
could lead
urllib3 to unnecessarily reparse the request URI. (<a
href="https://redirect.github.com/psf/requests/issues/6644">#6644</a>)</li>
</ul>
<p><strong>Deprecations</strong></p>
<ul>
<li>Requests has officially added support for CPython 3.12 (<a
href="https://redirect.github.com/psf/requests/issues/6503">#6503</a>)</li>
<li>Requests has officially added support for PyPy 3.9 and 3.10 (<a
href="https://redirect.github.com/psf/requests/issues/6641">#6641</a>)</li>
<li>Requests has officially dropped support for CPython 3.7 (<a
href="https://redirect.github.com/psf/requests/issues/6642">#6642</a>)</li>
<li>Requests has officially dropped support for PyPy 3.7 and 3.8 (<a
href="https://redirect.github.com/psf/requests/issues/6641">#6641</a>)</li>
</ul>
<p><strong>Documentation</strong></p>
<ul>
<li>Various typo fixes and doc improvements.</li>
</ul>
<p><strong>Packaging</strong></p>
<ul>
<li>Requests has started adopting some modern packaging practices.
The source files for the projects (formerly <code>requests</code>) is
now located
in <code>src/requests</code> in the Requests sdist. (<a
href="https://redirect.github.com/psf/requests/issues/6506">#6506</a>)</li>
<li>Starting in Requests 2.33.0, Requests will migrate to a PEP 517
build system
using <code>hatchling</code>. This should not impact the average user,
but extremely old
versions of packaging utilities may have issues with the new packaging
format.</li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/matthewarmand"><code>@​matthewarmand</code></a>
made their first contribution in <a
href="https://redirect.github.com/psf/requests/pull/6258">psf/requests#6258</a></li>
<li><a href="https://github.com/cpzt"><code>@​cpzt</code></a> made their
first contribution in <a
href="https://redirect.github.com/psf/requests/pull/6456">psf/requests#6456</a></li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/psf/requests/blob/main/HISTORY.md">requests's
changelog</a>.</em></p>
<blockquote>
<h2>2.32.0 (2024-05-20)</h2>
<p><strong>Security</strong></p>
<ul>
<li>Fixed an issue where setting <code>verify=False</code> on the first
request from a
Session will cause subsequent requests to the <em>same origin</em> to
also ignore
cert verification, regardless of the value of <code>verify</code>.
(<a
href="https://github.com/psf/requests/security/advisories/GHSA-9wx4-h78v-vm56">https://github.com/psf/requests/security/advisories/GHSA-9wx4-h78v-vm56</a>)</li>
</ul>
<p><strong>Improvements</strong></p>
<ul>
<li><code>verify=True</code> now reuses a global SSLContext which should
improve
request time variance between first and subsequent requests. It should
also minimize certificate load time on Windows systems when using a
Python
version built with OpenSSL 3.x. (<a
href="https://redirect.github.com/psf/requests/issues/6667">#6667</a>)</li>
<li>Requests now supports optional use of character detection
(<code>chardet</code> or <code>charset_normalizer</code>) when
repackaged or vendored.
This enables <code>pip</code> and other projects to minimize their
vendoring
surface area. The <code>Response.text()</code> and
<code>apparent_encoding</code> APIs
will default to <code>utf-8</code> if neither library is present. (<a
href="https://redirect.github.com/psf/requests/issues/6702">#6702</a>)</li>
</ul>
<p><strong>Bugfixes</strong></p>
<ul>
<li>Fixed bug in length detection where emoji length was incorrectly
calculated in the request content-length. (<a
href="https://redirect.github.com/psf/requests/issues/6589">#6589</a>)</li>
<li>Fixed deserialization bug in JSONDecodeError. (<a
href="https://redirect.github.com/psf/requests/issues/6629">#6629</a>)</li>
<li>Fixed bug where an extra leading <code>/</code> (path separator)
could lead
urllib3 to unnecessarily reparse the request URI. (<a
href="https://redirect.github.com/psf/requests/issues/6644">#6644</a>)</li>
</ul>
<p><strong>Deprecations</strong></p>
<ul>
<li>Requests has officially added support for CPython 3.12 (<a
href="https://redirect.github.com/psf/requests/issues/6503">#6503</a>)</li>
<li>Requests has officially added support for PyPy 3.9 and 3.10 (<a
href="https://redirect.github.com/psf/requests/issues/6641">#6641</a>)</li>
<li>Requests has officially dropped support for CPython 3.7 (<a
href="https://redirect.github.com/psf/requests/issues/6642">#6642</a>)</li>
<li>Requests has officially dropped support for PyPy 3.7 and 3.8 (<a
href="https://redirect.github.com/psf/requests/issues/6641">#6641</a>)</li>
</ul>
<p><strong>Documentation</strong></p>
<ul>
<li>Various typo fixes and doc improvements.</li>
</ul>
<p><strong>Packaging</strong></p>
<ul>
<li>Requests has started adopting some modern packaging practices.
The source files for the projects (formerly <code>requests</code>) is
now located
in <code>src/requests</code> in the Requests sdist. (<a
href="https://redirect.github.com/psf/requests/issues/6506">#6506</a>)</li>
<li>Starting in Requests 2.33.0, Requests will migrate to a PEP 517
build system
using <code>hatchling</code>. This should not impact the average user,
but extremely old
versions of packaging utilities may have issues with the new packaging
format.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="d6ebc4a2f1"><code>d6ebc4a</code></a>
v2.32.0</li>
<li><a
href="9a40d12778"><code>9a40d12</code></a>
Avoid reloading root certificates to improve concurrent performance (<a
href="https://redirect.github.com/psf/requests/issues/6667">#6667</a>)</li>
<li><a
href="0c030f78d2"><code>0c030f7</code></a>
Merge pull request <a
href="https://redirect.github.com/psf/requests/issues/6702">#6702</a>
from nateprewitt/no_char_detection</li>
<li><a
href="555b870eb1"><code>555b870</code></a>
Allow character detection dependencies to be optional in post-packaging
steps</li>
<li><a
href="d6dded3f00"><code>d6dded3</code></a>
Merge pull request <a
href="https://redirect.github.com/psf/requests/issues/6700">#6700</a>
from franekmagiera/update-redirect-to-invalid-uri-test</li>
<li><a
href="bf24b7d8d1"><code>bf24b7d</code></a>
Use an invalid URI that will not cause httpbin to throw 500</li>
<li><a
href="2d5f54779a"><code>2d5f547</code></a>
Pin 3.8 and 3.9 runners back to macos-13 (<a
href="https://redirect.github.com/psf/requests/issues/6688">#6688</a>)</li>
<li><a
href="f1bb07d39b"><code>f1bb07d</code></a>
Merge pull request <a
href="https://redirect.github.com/psf/requests/issues/6687">#6687</a>
from psf/dependabot/github_actions/github/codeql-act...</li>
<li><a
href="60047ade64"><code>60047ad</code></a>
Bump github/codeql-action from 3.24.0 to 3.25.0</li>
<li><a
href="31ebb8102c"><code>31ebb81</code></a>
Merge pull request <a
href="https://redirect.github.com/psf/requests/issues/6682">#6682</a>
from frenzymadness/pytest8</li>
<li>Additional commits viewable in <a
href="https://github.com/psf/requests/compare/v2.31.0...v2.32.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=requests&package-manager=pip&previous-version=2.31.0&new-version=2.32.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/openvinotoolkit/openvino/network/alerts).

</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-05-21 06:52:45 +00:00
Andrzej Kopytko 05867f2f63
[DOCS] fix css class (#24602) 2024-05-21 06:46:43 +00:00
Zhang Yi 4a9cd7bd87
[CPU][FP16]Fix GatherCompressed with FP16 scale (#24315)
### Details:
- *This PR https://github.com/openvinotoolkit/openvino/pull/23384
triggers the existing bugs in `GatherCompressed` and `Fullyconnected`*
- *After converting all possible constants to FP16, `GatherCompresssed`
needs to output `FP16` when scale is changed to FP16*
- *After converting all possible constants to FP16, `FullyConnected`
needs to explicitly refuse `FP16` bias since `oneDNN` doesn't support
`FP16` bias.*

### Tickets:
 - *CVS-140154*
2024-05-21 06:45:14 +00:00
Tingqian Li e6667f3bb9
[CPU] Fc support float16 weight (#24155)
### Details:
 - *Add support for (src_f32, weight_f16) case in FC*

oneDNN-fork PR: https://github.com/openvinotoolkit/oneDNN/pull/246

### Tickets:
 - *CVS-133453*
 - *CVS-139274*
2024-05-21 06:44:04 +00:00
Fang Xu 0e6c199db5
set correct numa id for different tbb version (#24532)
### Details:
 - *set correct numa id for different tbb version*
- *numa id has different mapping method in TBBBind since oneTBB
2021.4.0*

### Tickets:
 - *CVS-141067*
2024-05-21 05:09:35 +00:00
Wang, Yang 01de8469a0
[AUTO] Load cached model to target device W/O CPU accelerating (#24211)
### Details:
 - enable AUTO to retrieve the hash id for cached model
- load cached model to GPU only with AUTO if cached blob exists and not
set `ov::intel_auto::enable_startup_fallback` explicitly to AUTO

### Tickets:
 - CVS-140059
2024-05-21 04:39:29 +00:00
Eddy Kim 415ba28201
[GPU] updates to build some selected kernels in separate batches (#24499)
### Details:
- This PR updates the `kernels_cache` to build the selected kernels in
separate batches.
- This is a temporary WA to resolve performance degradation when some
kernels are built with other kernels in the same batch
   - Currently, the selected kernel includes `gemm_tiled_opt`.
- The impacted scenario : Qwen INT4 first token latency for > 1K input
in MTL

### Tickets:
 - GSD-8910
2024-05-21 03:18:01 +00:00
Taylor Yeonbok Lee 7545929163
[GPU] Fix set_state to handle original Tensor's padding (#24579)
### Details:
- In set_state of gpu plugin, the src Tensor can have padding, which has
not handled by set_state
 - Fixed set_state to handle src Tensor's padding properly 

### Tickets:
 - 140418
2024-05-20 21:35:57 +00:00
Maxim Vafin e9d42dd60b
[PT FE] Fix regression in easyocr model (#24586)
### Details:
- *After support for i64 was added in frontend `aten::adaptive_avg_pool`
started to fail if shape input is list.*

### Tickets:
 - *CVS-141335*
2024-05-20 16:51:30 +00:00
Roman Kazantsev 474a77a125
[MO] Remove test-generator dependency (#24576)
**Details:** Remove test-generator dependency. It is removed since this
module seems to be no longer developed and maintained. So it is better
to remove this dependency. `pytest` can substitute `test-generator`.

**Ticket:** TBD

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-05-20 15:55:16 +00:00
Evgenya Nugmanova bb8da80a59
Abs value inference and optimization (#24526)
### Details:
PyTorch semantic of Expand operation requires Abs operation for
translation which is usually a no-op.

1. partial value and symbol propagation for Abs operation
2. optimize out the Abs with nonnegative input
3. for this case Abs(Concat([Gather(ShapeOf), -1, 1, -1])) pulls Abs and
tries to const-fold it. Resulting in Concat([Abs(Gather(ShapeOf)), 1, 1,
1]). Applies (2) to the graph and gets Concat([Gather(ShapeOf), 1, 1,
1]) because ShapeOf's lower bound is 0.

### Tickets:
 - *CVS-141274*
2024-05-20 15:02:26 +00:00
Jan Iwaszkiewicz 380e10e217
[PyOV] Reenable test_cancel (#24590)
### Details:
 - Do not skip the test of `InferReuqest.cancel()`

### Tickets:
 - *CVS-95967*
2024-05-20 14:57:33 +00:00
Alicja Miloszewska 0eb8a42105
[OV JS] Remove acceptable_types parameter from js_to_cpp() template function (#24459)
### Details:
- Remove `const std::vector<napi_types>& acceptable_types` param from
template `TargetType js_to_cpp(const Napi::Value&, const
std::vector<napi_types>& acceptable_types);`
- Remove template specialization `int32_t js_to_cpp<int32_t>(const
Napi::CallbackInfo& info,
                           const size_t idx,
const std::vector<napi_types>& acceptable_types);`

### Tickets:
 - *140428*
2024-05-20 14:51:32 +00:00
Katarzyna Mitrus 05f99642b2
[Op][RMSNorm] Move RMSNorm from opset15 to dev_api (#24567)
### Details:

As ov RMSNorm has been not released yet as a public opset op, it was
proposed to keep it as internal.
RMSNorm is not currently a part of any frontend framework and the
requirements for RMSNorm may change.
There is a corresponding
[`internal::RMS`](70142121c1/src/common/transformations/include/ov_ops/rms.hpp)
op availavble for common transformations (moved from custom GPU).
The goal is to unify this work and tests into single RMS implementation.

---------------------------

The reference implementation is going to be reused for the
internal::RMS:
- https://github.com/openvinotoolkit/openvino/pull/24556

### Tickets:
 - Related to: 129027
2024-05-20 14:19:43 +00:00
Luo Cheng bc9ce91564
[CPU][Core] Update context_lens to the new spec for PageAttention (#24591)
### Details:
 - *Change the context_lens to past_lens*
- *past lens corresponds to first token within subgroup of scheduled
tokens but not includes itself*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-20 19:17:36 +04:00
Andrzej Kopytko 350c021870
[Docs] Button styling (#24593)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-20 13:38:30 +00:00
Michal Miotk 7a009aca63
[GPU] reducing permute_ref usage (#24393)
### Details:
- uncommented 2 divisor gives performance gain and enables models with
f==2 or y==2 to use permute_f_y kernel
### Tickets:
 - 140462
2024-05-20 13:33:43 +00:00
Alexandra Sidorova 80eb61a854
[Snippets] Added Configurator support (#21922)
### Details:
- *Added `RuntimeConfigurator` support to configure runtime arguments
(loop parameters, data offsets) for each static shapes in dynamic case.*
- *Added Shape-Agnostic dynamism for Eltwise subgraphs (disabled by
default)*


### Tickets:
 - *113211*
 - *139795*
 - *136157*
 - *139796*
 - *139785*

### Prerequisites:
- https://github.com/openvinotoolkit/openvino/pull/21934
- https://github.com/openvinotoolkit/openvino/pull/21881
- https://github.com/openvinotoolkit/openvino/pull/21895
- https://github.com/openvinotoolkit/openvino/pull/23710
- https://github.com/openvinotoolkit/openvino/pull/24115
- https://github.com/openvinotoolkit/openvino/pull/24119

### TODO:
- [x] Add `ShapeInfer` caching
- [x] Fix all failed tests
2024-05-20 12:54:06 +00:00
Anastasia Kuporosova 7f99b88420
[PyOV] python op implementation (#24487)
### Details:
 - based on: https://github.com/openvinotoolkit/openvino/pull/23612

### Tickets:
 - CVS-141051

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-20 12:40:17 +00:00
Andrzej Kopytko 09bee2e444
Docs update main page for master (#24589)
Fixed github icon
2024-05-20 12:10:55 +00:00
Jacek Pawlak ffb17325e1
Libxsmm licensing (#24565)
Added licensing for libxsmm

Ref PR: https://github.com/openvinotoolkit/openvino/pull/22210/
2024-05-20 11:42:12 +00:00
Attila Csok f675d14608
[intel-npu] Adding EXECUTION_DEVICES read-only property (#24531)
### Details:
 - Adding EXECUTION_DEVICES read-only property for intel-npu plugin.

### Tickets:
 - EISW-112990
2024-05-20 11:41:02 +00:00
Fang Xu 9a78d5f927
fix compilation issue on ubuntu24 (#24580)
### Details:
 - *fix compilation issue on ubuntu24*

### Tickets:
 - *141313*
2024-05-20 11:15:25 +00:00
Roman Kazantsev b6609e830f
[TF FE] Support adjoint mode for MatrixInverse operation (#24581)
**Details:** After fix
https://github.com/openvinotoolkit/openvino/pull/24071, we are ready
support `adjoint` for MatrixInverse

**Ticket:** TBD

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-05-20 11:07:54 +00:00
Taylor Yeonbok Lee fe8c4445f6
[GPU] Enable permute + onednn gemm fusion for dynamic shape (#24563)
### Details:
 -  Enable permute + onednn gemm fusion for dynamic shape
 -  Fix unittests to test various permute orders fused with gemm
- This pr has dependency on onednn change on memory tag. Do not merge
until the memory tag change is ready

### Tickets:
 - 138961
2024-05-20 09:38:15 +00:00
Edward Shogulin 9049d746db
[CPU] [ARM] JIT Mish (#24222)
### Details:
 - *[CPU] [ARM] JIT Mish*

### Tickets:
 - *CVS-139718*
2024-05-20 08:57:38 +00:00
yanlan song c8007abcb7
fix AUTO wrong device selection logic if dynamic stateful model (#24442)
### Details:
 - check dynamic + stateful logic

### Tickets:
 - CVS-140254, CVS-140844

---------

Signed-off-by: fishbell <bell.song@intel.com>
Co-authored-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
2024-05-20 08:50:08 +00:00
Vladislav Golubev 63b19000ea
[CPU] Shared compressed weights support (#24117)
### Details:
- *Shared decompression between 2 Matmuls is supported for 8bits and
4bits weights*
- *Shared decompression between Matmul and Gather is supported for 8bits
and 4bits weights*
 - *Added CPU subgraph test*

### Tickets:
 - *CVS-140442* <= Validation results can be found there
 - *CVS-137591*
 - *CVS-136594*
2024-05-20 08:47:18 +00:00
Vladimir Paramuzov d14df95b40
[GPU] Unit test fixes (#24380)
### Details:
 - Use float for intermediate calculation of grid sample op
 - Adjust data ranges for fc unit test to avoid huge numbers

### Tickets:
 - *CVS-134015*
2024-05-20 08:20:45 +00:00
cecilia peng 5cb1660f3a
[CPU ]fix axis out of boundary issue in SEU impl. (#24561)
### Details:
 - *a simple fix to SEU impl and check axis validity*

### Tickets:
 - *141188*
2024-05-20 07:41:24 +00:00
Piotr Krzemiński d6c4775e54
[Reference][CPU] Inverse correctly computes adjoint (#24071)
### Details:
 - Changed from the adjugate matrix to transpose of the matrix

### Tickets:
 - 138715

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2024-05-20 07:14:30 +00:00
Maxim Vafin 87d6f201aa
[PT FE] Support converting 16bit models by patching (#24482)
### Details:
- *Add patch function to make 16bit models traceable. This reduce memory
consumption and time spent during conversion of models that are natively
saved in 16bit precision*

### Tickets:
 - *CVS-136828*
2024-05-20 07:08:03 +00:00
Maxim Vafin ab6e0f8333
[PT FE] Support inplace aten::sqrt, aten::rsqrt, aten::clamp_{min, max} (#24354)
### Details:
- *Support inplace `aten::sqrt_`, `aten::rsqrt_`, `aten::clamp_min_`,
`aten::clamp_max_`*

### Tickets:
 - *ticket-id*
2024-05-20 07:05:23 +00:00
Vladimir Paramuzov 38fdcbab78
[GPU] Avoid force exit for out of resource exception if device is lost (#23826)
### Details:
- Improved CL_OUT_OF_RESOURCES exception handling to avoid force exit
when device is lost
2024-05-20 06:34:23 +00:00
David Nam bcf8449dcf
[GPU] Fix NMS cpu impl (#24451)
### Details:
- In case of multiple images and iterations, the calculation of NMS
output shape was incorrect

### Tickets:
 - 136451
2024-05-20 03:26:43 +00:00
dependabot[bot] 3ac498dd86
Bump jinja2 from 3.1.3 to 3.1.4 in /docs (#24557)
Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.3 to 3.1.4.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/pallets/jinja/releases">jinja2's
releases</a>.</em></p>
<blockquote>
<h2>3.1.4</h2>
<p>This is the Jinja 3.1.4 security release, which fixes security issues
and bugs but does not otherwise change behavior and should not result in
breaking changes.</p>
<p>PyPI: <a
href="https://pypi.org/project/Jinja2/3.1.4/">https://pypi.org/project/Jinja2/3.1.4/</a>
Changes: <a
href="https://jinja.palletsprojects.com/en/3.1.x/changes/#version-3-1-4">https://jinja.palletsprojects.com/en/3.1.x/changes/#version-3-1-4</a></p>
<ul>
<li>The <code>xmlattr</code> filter does not allow keys with
<code>/</code> solidus, <code>&gt;</code> greater-than sign, or
<code>=</code> equals sign, in addition to disallowing spaces.
Regardless of any validation done by Jinja, user input should never be
used as keys to this filter, or must be separately validated first.
GHSA-h75v-3vvj-5mfj</li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/pallets/jinja/blob/main/CHANGES.rst">jinja2's
changelog</a>.</em></p>
<blockquote>
<h2>Version 3.1.4</h2>
<p>Released 2024-05-05</p>
<ul>
<li>The <code>xmlattr</code> filter does not allow keys with
<code>/</code> solidus, <code>&gt;</code>
greater-than sign, or <code>=</code> equals sign, in addition to
disallowing spaces.
Regardless of any validation done by Jinja, user input should never be
used
as keys to this filter, or must be separately validated first.
:ghsa:<code>h75v-3vvj-5mfj</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="dd4a8b5466"><code>dd4a8b5</code></a>
release version 3.1.4</li>
<li><a
href="0668239dc6"><code>0668239</code></a>
Merge pull request from GHSA-h75v-3vvj-5mfj</li>
<li><a
href="d655030770"><code>d655030</code></a>
disallow invalid characters in keys to xmlattr filter</li>
<li><a
href="a7863ba9d3"><code>a7863ba</code></a>
add ghsa links</li>
<li><a
href="b5c98e78c2"><code>b5c98e7</code></a>
start version 3.1.4</li>
<li><a
href="da3a9f0b80"><code>da3a9f0</code></a>
update project files (<a
href="https://redirect.github.com/pallets/jinja/issues/1968">#1968</a>)</li>
<li><a
href="0ee5eb41d1"><code>0ee5eb4</code></a>
satisfy formatter, linter, and strict mypy</li>
<li><a
href="20477c6357"><code>20477c6</code></a>
update project files (<a
href="https://redirect.github.com/pallets/jinja/issues/5457">#5457</a>)</li>
<li><a
href="e491223739"><code>e491223</code></a>
update pyyaml dev dependency</li>
<li><a
href="36f98854c7"><code>36f9885</code></a>
fix pr link</li>
<li>Additional commits viewable in <a
href="https://github.com/pallets/jinja/compare/3.1.3...3.1.4">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=jinja2&package-manager=pip&previous-version=3.1.3&new-version=3.1.4)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/openvinotoolkit/openvino/network/alerts).

</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-05-19 20:29:21 +00:00
Adithya Hegde Kota 7061e92a2d
Expose Model.get_output_shape() method to Node.js API (#23843)
### Details:
A method `get_output_shape()` to the Model class in the Node.js API of
OpenVINO framework.This method would allow users to retrieve the output
shape of a model, which is useful for understanding the model's output
data.

### Implemented 
- [x] add get_output_shape() method on C++ side
(src/bindings/js/node/src/model.cpp)
- [x] update TypeScript definition (src/bindings/js/node/lib/addon.ts)
- [x] create unit test for added functionality using Node.js Test Runner

Fixes #23568

---------

Co-authored-by: Vishniakov Nikolai <nikolai.vishniakov@intel.com>
2024-05-18 21:32:08 +00:00
Xuejun Zhai 7e64e416b5
Force default locale for cache model write/read (#24431)
### Details:
- Check the value of setlocale for export/import, if different with "C"
will set to "C" and record the original value, after export/import done
will reset to the original.
- *Fix the error caused by pugixml library with The setlocale function
installs the specified system locale or its portion as the new C locale.
different C may return unexpected results with setlocal()*

### Tickets:
 - https://github.com/openvinotoolkit/openvino/issues/24370

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
Co-authored-by: River Li <river.li@intel.com>
2024-05-17 18:13:56 +00:00
Piotr Kowalczyk b2db8b4370
[GPU]: Added ROIAlignRotated basic impl (#23955)
### Details:
 - Added support for ROIAlignRotated with tests.
 - Fixed 3 bugs in ROIAlign impl.

### Tickets:
 - *135849*

---------

Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
2024-05-17 15:36:05 +00:00
Haiqi Pan 24891bdabc
Remove specific plugin names in shared test case (#24129)
### Details:
 - *Remove specific plugin names in shared test case*
- *Throw exception if device list in both ov::device::priorities() and
device name (For example AUTO:GPU,CPU)*


### Tickets:
 - *CVS-130214*

---------

Co-authored-by: Chen Peter <peter.chen@intel.com>
2024-05-17 15:24:04 +00:00
Edward Shogulin 31d01fcd10
[CPU] [ARM] HardSigmoid decompoition & JIT exec (#24174)
### Details:
 - *[CPU] [ARM] HardSigmoid decompoition & JIT exec*
 - dependency: https://github.com/openvinotoolkit/openvino/pull/24165

### Tickets:
 - *CVS-139363*
2024-05-17 15:03:27 +00:00
Aleksandr Voron 3b54cce8ef
[CPU][ARM] Upgrade ACL to 24.04 (#24491) 2024-05-17 13:59:11 +00:00
Jan Iwaszkiewicz b997614f92
[PyOV] Add stateful API to CompiledModel (#24545)
### Details:
- Extended stateful API to CompiledModel class to allow working on
underlaying InferRequest.
 - Added test cases and refactored them.

### Tickets:
 - CVS-139972
2024-05-17 12:53:59 +00:00
Vladimir Paramuzov 7ffea61c64
[GPU] Improve swiglu fusion pass (#24537)
### Details:
 - Allow reversed inputs order to last multiply op for swiglu pattern
2024-05-17 12:23:28 +00:00
Nikolay Shchegolev 88b0309830
[CPU] Support inference_precision::undefined in CPU and use it in ExecutionMode::ACCURACY (#24118)
### Details:
- *Support inference_precision::undefined in CPU and use it in
ExecutionMode::ACCURACY*

### Tickets:
 - *136167*
2024-05-17 11:57:37 +00:00
Vladimir Paramuzov 3f3c86ddad
[GPU] Shape infer for remaining ops (#24440)
### Details:
- Added `calc_output_layouts()` impl for remaining operations, so since
that patch all ops have new shape infer method, so we can start
migration to the new path and removal of the legacy shape infer
- Added RotateNMS handling in
`non_max_suppression_inst::calc_output_layouts`
 - Pass max iterations count in loop shape infer
 - Added second out handling in pooling primitive
- Added PSROIPooling and DeformablePSROIPooling handling in
`roi_pooling_inst::calc_output_layouts`
- Updated gpu tensor accessor to return empty tensor for non-existing
dependency instead of exception to simplify usages
2024-05-17 11:51:30 +00:00
Tomasz Jankowski 5dfd2953bd
[Tmpl test] Range: Drop legacy comparison (#24555)
### Details:
 - Added actual shape to expected output tensor.
 - Removed useless code.

### Tickets:
 - CVS-137198
2024-05-17 10:24:21 +00:00
Michal Miotk e6164d6c96
[Op] Common RMS operation - corrected author (#24539)
Details:
-move RMS operation to common internal opset
-move RMS fusion transformation to common part
-based on https://github.com/openvinotoolkit/openvino/pull/24057
Tickets:
138554
2024-05-17 10:06:08 +00:00
barnasm1 2353fb7a58
[CORE] Change get_input_const_data_as return type from std::unique_ptr to ov::optional (#24443)
### Details:
 - Return type replaced
 - Checked if binary size decreased.

### Tickets:
 - CVS-111396

---------

Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
2024-05-17 10:05:33 +00:00
Tomasz Jankowski ef0eb433a1
[Tmpl test] Enable whole Tensor comparison (#24527)
### Details:
- Added actual shape to expected output tensor in tests for RegionYolo,
ROIPooling, Select, SquaredDifference and Unique.

### Tickets:
 - CVS-137200, CVS-137208, CVS-137209, CVS-137210, CVS-137213
2024-05-17 10:05:30 +00:00
Yury Gaydaychuk 8a4d87b66d
[Commit slider] bm template extended (#24550)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-17 10:00:35 +00:00
Maxim Vafin 8e8801f386
[PT FE] Support torch.any and torch.all on both FX and TS side (#24553)
### Details:
 - *Support torch.any and torch.all on both FX and TS side*
 - *Support aten::isfinite, aten::isinf and aten::isnan*

### Tickets:
 - *ticket-id*
2024-05-17 09:13:28 +00:00
Andrei Kashchikhin 9da7f72dcf
[CI] [GHA] Use Dockerfiles in Linux CC workflow (#24395)
### Tickets:
 - *140538*
2024-05-17 09:12:22 +00:00
Wang Wangwang 03aad66230
[DOCS] Update the document of HETERO pipeline parallelism (#24470)
### Details:
 - Update the document of HETERO pipeline parallelism

### Tickets:
 - *CVS-138199*
2024-05-17 08:27:48 +00:00
Eddy Kim 5495b66e96
[GPU] adding a new convolution_gpu_bfyx_os_iyx_osv32 kernel (#24465)
### Details:
- In dynamic models, only the `convolution_gpu_bfyx_os_iyx_osv16` kernel
has been used, which was one of the reasons for the performance gap
between the static and dynamic models.
- This PR adds a new `convolution_gpu_bfyx_os_iyx_osv32` kernel for
better performance of dynamic models.

### Tickets:
 - 134700
2024-05-17 07:36:33 +00:00
Mingyu Kim 9fadb5ac64
[GPU] Reduce binary size by disabling unused isa (#24543)
### Details:
 - GPU plugin binary size reduction
2024-05-17 07:08:44 +00:00
Andrzej Kopytko 05922dc3d1
[Docs] port benchmark files RC2 to master (#24549)
Port for:
https://github.com/openvinotoolkit/openvino/pull/24409
https://github.com/openvinotoolkit/openvino/pull/24528
2024-05-17 06:31:21 +00:00
Edward Shogulin 89b02da9d1
[CPU] [ARM] JIT Elu (#24210)
### Details:
 - *[CPU] [ARM] JIT Elu*

### Tickets:
 - *CVS-139593*
2024-05-17 05:51:26 +00:00
Fang Xu d28db5a53d
update onetbb2021.2.5 for linux arm64 and mac arm64 (#24484)
https://github.com/oneapi-src/oneTBB/releases/tag/v2021.2.5

### Details:
 - *update onetbb2021.2.5 for linux arm64 and mac arm64*
- *onetbb2021.2.5:
https://github.com/oneapi-src/oneTBB/releases/tag/v2021.2.5*

### Tickets:
 - *140409*

---------

Co-authored-by: Chen Peter <peter.chen@intel.com>
2024-05-17 05:27:15 +00:00
Ilya Lavrenov 92e88b28e7
Use custom TBB even on Linux (#24359)
### Details:
- System TBB provides lower performance than newer versions, so we have
to distribute our own one.
2024-05-17 09:07:41 +04:00
Xiping Yan fc5e60c77e
fix regression model orca (#24100)
### Details:
 - *Fix regression for model orca.*
 - *Add test to conver orca for CPU/GPU test.*

### Tickets:
 - *138406*

---------

Signed-off-by: xipingya <xiping.yan@intel.com>
2024-05-17 01:49:23 +00:00
Luo Cheng 61822be8ff
[CPU][Core] PageAttention supports new interface (#24538)
### Details:
This is subsequent PR of
https://github.com/openvinotoolkit/openvino/pull/24107
 - *Core part*
    - updated PA op for new interface
    - updated transform for new PA op
    - fix in transformation infrastructure
 - *CPU part*
    - supports new interface
    - alibi support
    - coverity issue
   
TODO:
  - supports head size is not multiple of 16
  - supports block size is multiple of 32

### Tickets:
 - *[140599](https://jira.devtools.intel.com/browse/CVS-140599)*
 - *[137724](https://jira.devtools.intel.com/browse/CVS-137724)*
 - *[139803](https://jira.devtools.intel.com/browse/CVS-139803)*

---------

Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
Co-authored-by: Tikhonov Ivan <ivan.tikhonov@intel.com>
2024-05-16 18:04:21 +04:00
Maciej Smyk 2f313179d0
[DOCS] Assets move - snippets for master (#24510)
Jira: 138084

Moving snippets assets closer to the source files.
2024-05-16 11:47:29 +00:00
Przemyslaw Wysocki 9280cec95c
[Opset15][Spec] Col2Im-15 specification (#23947)
### Details:
- Similar in functionality to
https://pytorch.org/docs/stable/generated/torch.nn.Fold.html, `Col2Im`
is `torch.nn.Fold` restricted to two output spatial dimensions
- Some `Col2Im` related discussions:
https://github.com/openvinotoolkit/openvino/issues/20549

### Related PRs
- https://github.com/openvinotoolkit/openvino/pull/24197

### Tickets:
 - CVS-133358
2024-05-16 11:04:43 +00:00
Evgeny Kotov 1a87846033
[transpose sinking] fix SIGSEGV TSDataMovement (#24132)
### Details:
 - check constant is not empty

### Tickets:
 - CVS-138875
2024-05-16 10:23:43 +00:00
Wang Wangwang 7d7fdbe435
Fix the error of splitting chatglm, qwen-7b-chat and baichuan-13b (#24389)
### Details:

- When there are some submodels need to be merged into one model, if
there is a independent submodel in the submodels, such as `chatglm,
qwen-7b-chat`:
submodel A (independent )
submodel B
submodel C
B and C will be the same because they have connection(input/output), so
when merge C into A after B merged, it will throw `parameters already
added` errior in add_parameters().
So add a distinct_submodels_index set to store the distinct submodels
will be merged.

- When split `baichuan-13b` into 2 parts, it will has error: Model
references undeclared parameters: opset1::Parameter input_ids () ->
(i64[?,?]), because there are some ops not removed correctly.

### Tickets:
 - *CVS-140527*
2024-05-16 10:18:03 +00:00
tadamczx 5b85cfe1ca
[DOCS] fix openvino_custon_sphinx_sitemap installation (#24536)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-16 09:42:14 +00:00
Irina Efode 98b0a3ac9f
[ TRANSFORMATIONS TESTS POC] Extending conformance tools to work with transformed graphs (#24478)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-16 09:18:39 +00:00
Xiping Yan df257c52a6
cpu_convert enable u4/i4 ->f32,bf16,i8,u8 (#24297)
### Details:
 - *cpu_convert enable u4/i4 -> f32/bf16/i8/u8*

### Tickets:
 - *124834*
 - *139282*
 - *140112*

---------

Signed-off-by: xipingya <xiping.yan@intel.com>
2024-05-16 07:16:55 +00:00
Pawel Raasz 74829b1ad2
[core] Use custom functions in reference binary ops impl (#24444)
### Details:
- Custom function used in binary element wise operators to reduce bin
size (around 130k).

### Tickets:
 - [CVS-138266](https://jira.devtools.intel.com/browse/CVS-138266)
2024-05-16 06:38:44 +00:00
Edward Shogulin 8d6bb92764
[CPU] [ARM] JIT HSigmoid: Min & Max (#24165)
### Details:
 - *[CPU] [ARM] JIT HSigmoid: Min & Max*

### Tickets:
 - *CVS-139331*
2024-05-16 06:09:24 +00:00
Mingyu Kim 4126988bbd
[GPU] OneDNN v3.5 update and fix for OOB memory access (#24411)
### Details:
 - Update OneDNN to v3.5
 - Fix OOB memory access with fake alignment
- Do not fake-align if input-memory is not allocated properly (it
impacts test cases where FC gets input from data node)
- This fix is applied only to some hardware because of performance
concern

### Tickets:
 - 141215
 - 138012
2024-05-16 05:22:46 +00:00
Luwei Zhou 9a80d31c6b
[CPU] brgconv on AVX2 enabling and switch OV deconv implement to ONEDNN deconv OP from conv_backward_data (#23596)
### Details:
- *Re-enable conv with brgemm implement on avx2 platform with fp32 ,
also heuristic cause by wavernn-upsampler regression*
- *Switch OV cpu deconv implement from ONEDNN convbackward_data
primitive to deconv primitive. Support const and non-const weight;
Always expose planar weight layout to cpu graph; weight cache to save
blocked const weight ; runtime reorder for none-const weight*
 - *enable bias fusing for fp32 to replace legacy depthwise fusing*
 - *enable deconv brgconv for fp32 and INT8 deconv*
 - *update test case*

### About test case/WA update:
- *OV has feature to set the output shape of conv_backward_data. Which
would cause pad_r < 0 && pad_r + dil < 0, so applied the WA in onednn to
create deconv OP*
- *Deconv only has one ref entry(CPU_INSTANCE(ref_deconvolution_fwd_t)
for JIT,gemm and c++ reference implement. So one layout can't use RTinfo
to filter implement. Update test cases with 1x1 related or SSE related.
     For example:  backward data has 2 entries when input is nChw16C :
       jit_avx512_common_1x1_convolution_bwd_data_f32_t 
      jit_avx512_common_convolution_bwd_data_t<f32> to support
So OV filter can work to get desired implement type. However, deconv
only has only, it means that nChw16C would only get one implement type.
So filter would not work.*
 - *Change stride to 1 unit because of brgemm limitation*
- *subgraph concat deconv test can't hit ref implement because the gemm
and ref share one entry implement.*
- *Conformance test conv related failed, but can pass when merging 3.3
with brg. Failed caused by
![PR22972](https://github.com/openvinotoolkit/openvino/pull/22972).
Seems threshold changes. Also AMX and avv512 core would fail on these
conformance test but not enabled on Azure platforms. Guess the expected
result is based on avx2 jit. So current just remove these test*

### Tickets:
 - *CVS-133120, CVS-122688*
2024-05-16 05:19:27 +00:00
Paul Youngsoo Ahn eb8cfe08d5
[GPU] Fix execution order corrupted issue on dGPU (#24283)
### Details:
- * Set needs_completion_event when current node has runtime skippable
users in primitive_inst ctor*
 - * Add marking runtime skippable for reorder in build time*

### Tickets:
 - *CVS-135257*
2024-05-16 04:06:11 +00:00
Attila Csok 066bb50e26
[intel-npu] Implementing DEVICE_TYPE property (#24530)
### Details:
 - Implementing DEVICE_TYPE property for intel-npu plugin
 - *...*

### Tickets:
 - EISW-112992
2024-05-15 21:42:22 +00:00
Alessandro de Oliveira Faria (A.K.A.CABELO) 5cff5d7e1d
OpenVINO at the openSUSE Factory - cabelo@opensuse.org (#24519)
@tadamczx and @ilya-lavrenov It took a while but I delivered what was
promised, openVINO at the official openSUSE factory. It took more than 6
months of work to get approval from the community...

---------

Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
2024-05-15 20:23:47 +00:00
Pawel Raasz 765302e0de
Fuzzer test print ASAN file path used for OV build (#24508)
### Details:
- Add additional information how use fuzzer tests when OV build as
shared library.

### Tickets:
 - [CVS-140764](https://jira.devtools.intel.com/browse/CVS-140764)
2024-05-15 16:55:10 +00:00
Anastasiia Pnevskaia 8229da4c0e
Remove update version reminder. (#24513)
### Details:
- As it is not a common practice for PyPI packages to remind for
updating update reminder was decided to be removed.

### Tickets:
 - 89093
2024-05-15 15:50:26 +00:00
Chen Xu 68bdbbe0fb
[CPU] [Snippets] Snippets for ARM (#23180)
### Details:
 - ***Feature***

* *POC scope of Snippets on ARM architecture supports simple elementwise
(combinations of Add, Multiply, Divide, Relu, Exp and Tanh ops)
subgraphs for FP32 precision.*

 - ***Implementations***
   * *aarch64 CPU Generator and TargetMachine*
   * *aarch64 load/store emitters*
* *aarch64 control-flow emitters (Kernel, LoopBegin, LoopEnd,
BroadcastMove, Scalar, Fill)*


### Tickets:
 - *[134078](https://jira.devtools.intel.com/browse/CVS-134078)*
2024-05-15 14:39:23 +00:00
Attila Csok d2a2e7d21b
[intel-npu] implementing EXECUTION_MODE_HINT property (#24524)
### Details:
 - implementing EXECUTION_MODE_HINT property for intel-npu plugin
 - *...*

### Tickets:
 - EISW-120263
 - EISW-112993
 - https://jira.devtools.intel.com/browse/CVS-131808
2024-05-15 14:38:22 +00:00
Alexandra Sidorova 90c9bd18f4
[CPU] Created BrgemmCompiledKernel to cache palette with kernel (#24504)
### Details:
- *If there are several MHA-patterns with the same Brgemms inside (the
same configs), first Brgemm calls `compile_kernel` using executor:
initializes `palette` and compile `kernel`. The brgemm from the second
MHA finds in the cache this `kernel` by the config that is equal to
first Brgemm has. Hovewer, previously `palette` was stored in `config` -
this `config` is not cached and not shared between emitters. Thus,
second Brgemm had cached `kernel` and config with empty `palette` since
it's inited `compile_kernel` that is not called for this `Brgemm`. The
PR introduces new structure that contains `compiled_kernel` and
`palette` - these values are cached together and can be shared between
nodes and emitters*

### Tickets:
 - *140771*
2024-05-15 14:24:27 +00:00
Roman Kazantsev da66abcbe9
[Model Hub Tests] Fix caching for read_model scenario (#24355)
**Details:** Fix caching for read_model scenario

**Ticket:** TBD

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2024-05-15 13:58:54 +00:00
Piotr Kowalczyk cf5bf71802
[CPU]: Added ROIAlignRotated basic impl. (#23844)
### Details:
 - Added basic implementation of ROIAlignRotated
- It uses implementation from core::reference - the goal was just to add
support for the op, not the optimized implementation.
- No unit tests added, since impl is already tested by core::reference
and functional tests.

### Tickets:
 - [CVS-135847](https://jira.devtools.intel.com/browse/CVS-135847)

---------

Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
2024-05-15 12:53:08 +00:00
Bogdan Pereanu 3302535334
[SAMPLES] Get the correct batch size when running with pre-compiled models (#24507)
### Details:
 - *get the correct batch size when running with pre-compiled models*

### Tickets:
 - *CVS-140703*
2024-05-15 12:08:26 +00:00
tadamczx 058aed8bc7
Docs long build fix (#24406)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-15 11:59:53 +00:00
Anastasiia Pnevskaia 836dcf5efc
Made MO deprecation message more explicit. (#24512)
### Details:
 - Made MO deprecation message more explicit.
 - PyLint fixes

### Tickets:
 -
2024-05-15 11:56:55 +00:00
Vladislav Golubev eb1eb22931
[Snippets] TPP build fix (#24503) 2024-05-15 11:50:07 +00:00
Anastasia Kuporosova 0d68c8bc12
[PyOV] add set/add_names to Output (#24522)
### Details:
 - Add `set_names`/`add_names` to Output

### Tickets:
 - CVS-141246
2024-05-15 11:35:51 +00:00
Anastasia Kuporosova 4936b14568
Checkout OMZ to fetch numpy<2 restriction (#24523)
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
2024-05-15 10:46:07 +00:00
Anastasia Kuporosova 460604c887
[PyOV] Missed API for Node (#24427)
### Details:
 - Add missed methods for Node:
"get_input_element_type",
"get_input_partial_shape",
"get_input_shape",
"set_output_type",
"set_output_size",
"validate_and_infer_types"

### Tickets:
 - CVS-141050

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-15 10:41:18 +00:00
Jyothish Kumar M S 026ac9e353
Added Alpine Linux dependencies to install list (#24455)
### Details:
 - Added Alpine Linux dependencies to install list

### Tickets:
 - #24368
2024-05-15 14:50:30 +04:00
Luo Cheng 04a7ecfadf
[CPU] PagedAttention supports dynamic-split fuse (#24107)
### Details:
 - *Merge first token and second token inference into one parallel loop*
- *~~Additional optimization: pre-transpose k-cache, pre-pack v-cache if
needed~~*
- *Additional optimization for first token: save q * k' upper triangle
matrix computation and (q * k') * v lower triangle matrix computation*
- *C++ pipeline can enable it:
https://github.com/ilya-lavrenov/openvino.genai/pull/9*
 - *TODO(in another PR):*
   - alibi support
   - performance tuning
   - testcase

### Tickets:
 - *[138673](https://jira.devtools.intel.com/browse/CVS-138673)*
2024-05-15 12:46:14 +04:00
Andrii Staikov 6950460b34
Fix PagedAttention PrevSequenceLengthPattern pattern (#24514)
Fix PagedAttention PrevSequenceLengthPattern pattern

Fix pattern of PrevSequenceLengthPattern that makes it match twice than
needed resulting in the incorrect inference.
Provide the correct version of Gather (v8::Gather) and amend
PrevSequenceLengthPattern pattern for the correct matching.

Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>

### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*

Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2024-05-15 11:46:43 +04:00
himanshugupta11002 a2cd7be673
[BATCH] support ov::enable_profiling (#23265)
### Details:
To complete task-I added PERF_COUNT to the plugin.cpp
And To complete the task-2 I have added get_property_params() 

# Tickets:
#23075, CVS-130236
2024-05-14 13:06:03 +00:00
Vishniakov Nikolai 5cfefd768b
[OV JS] Add test of installation openvino-node package (#24404)
### Details:
- Based on this issue:
https://github.com/openvinotoolkit/openvino/issues/24015
2024-05-14 09:10:44 +00:00
Chen Peter 8c82c6044e
Update meta-plugin revalidate list (#24423)
### Details:
 - *meta-plugins are tested with dedicated test binaries*
 - *Remove CPU/GPU/TEMPLATE from meta-plugin revalidate list*
- *Keep GPU in AUTO-BATCH revalidate list since AUTO-BATCH is enabled by
default for GPU throughput mode*
- ***revalidate**: Includes the test cases which can be impacted by the
changes in this component*
- ***build**: Includes the dependencies for the test cases of this
component*

### Tickets:
 - *CVS-129316, CVS-129317, CVS-129319*

---------

Signed-off-by: Chen Peter <peter.chen@intel.com>
2024-05-14 08:57:47 +00:00
Nikolay Shchegolev b5b279cd2a
[CPU] Fix alloc-size-larger-than warning. (#24463)
### Details:
 - [CPU] Suppress alloc-size-larger-than warning

### Tickets:
 - CVS-140251
2024-05-14 08:32:50 +00:00
awayzjj 9f6783564b
[OP CONFORMANCE][TEMPLATE] Convolution tests are failed in opset conformance (#24162)
Closes https://github.com/openvinotoolkit/openvino/issues/23554
### Details:
 - Added static shapes generator
2024-05-14 07:18:08 +00:00
Przemyslaw Wysocki 239b57869f
[Op] Add `Col2Im-15` implementation to Core (#24197)
### Details:
 - Add Core implementation of `Col2Im-15`

### Related PRs
- https://github.com/openvinotoolkit/openvino/pull/23947

### Tickets:
 - CVS-138918

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2024-05-14 05:42:19 +00:00
Kelvin Choi 76052651d1
[GPU] Add i32 output type for FC (#23728)
### Details:
 - *Add i32 output type for FC*

### Tickets:
 - *100911*
2024-05-14 05:34:23 +00:00
Chen Xu e164cde452
[CPU] [Snippets] Update the state of current_loop_info after loop fusion (#24473)
### Details:
- *In FuseLoops pass, update the state of current_loop_info after loop
fusion, so that the state of port connections will be updated and some
other loops may fuse to the current loop.*

### Tickets:
 - *[CVS-141023](https://jira.devtools.intel.com/browse/CVS-141023)*
2024-05-14 04:01:30 +00:00
1884 changed files with 71708 additions and 20239 deletions

View File

@ -33258,7 +33258,7 @@ async function save() {
// remote cache directory may not be created yet
if (!(await checkFileExists(cacheRemotePath))) {
await fs.mkdir(cacheRemotePath);
await fs.mkdir(cacheRemotePath, { recursive: true });
}
core.info('Copying cache...');

View File

@ -33258,7 +33258,7 @@ async function save() {
// remote cache directory may not be created yet
if (!(await checkFileExists(cacheRemotePath))) {
await fs.mkdir(cacheRemotePath);
await fs.mkdir(cacheRemotePath, { recursive: true });
}
core.info('Copying cache...');

View File

@ -50,7 +50,7 @@ async function save() {
// remote cache directory may not be created yet
if (!(await checkFileExists(cacheRemotePath))) {
await fs.mkdir(cacheRemotePath);
await fs.mkdir(cacheRemotePath, { recursive: true });
}
core.info('Copying cache...');

View File

@ -23,7 +23,19 @@ runs:
using: 'composite'
steps:
- if: ${{ runner.os == 'Linux' && inputs.self-hosted-runner == 'true' }}
- name: Check if Python is already installed (Linux)
if: ${{ runner.os == 'Linux' }}
shell: bash
id: check_python
run: |
PYTHON_INSTALLED=$(python${{ inputs.version }} -V) || true
if [[ $PYTHON_INSTALLED ]]; then
echo "installed=true" >> $GITHUB_OUTPUT
else
echo "installed=false" >> $GITHUB_OUTPUT
fi
- if: ${{ runner.os == 'Linux' && inputs.self-hosted-runner == 'true' && steps.check_python.outputs.installed == 'false' }}
name: Install 'actions/setup-python@v4' dependencies
shell: bash
run: apt-get update && apt-get install -y ca-certificates software-properties-common gpg-agent tzdata
@ -31,18 +43,18 @@ runs:
DEBIAN_FRONTEND: noninteractive # to prevent apt-get from waiting user input
TZ: "Europe/London" # to prevent tzdata from waiting user input
- if: ${{ runner.os == 'Linux' && runner.arch == 'ARM64' }}
- if: ${{ runner.os == 'Linux' && runner.arch == 'ARM64' && steps.check_python.outputs.installed == 'false' }}
name: Setup sudo and python3
shell: bash
run: apt-get update && apt-get install -y sudo python3 # Needed for the deadsnakes action
- if: ${{ runner.os == 'Linux' && runner.arch == 'ARM64' }}
- if: ${{ runner.os == 'Linux' && runner.arch == 'ARM64' && steps.check_python.outputs.installed == 'false' }}
name: Setup Python ${{ inputs.version }}
uses: akashchi/deadsnakes-action@92417281055a5878a0450f240a5b95883eb2d7e2
with:
python-version: ${{ inputs.version }}
- if: ${{ runner.os == 'macOS' || runner.os == 'Windows' || (runner.os == 'Linux' && runner.arch != 'ARM64') }}
- if: ${{ runner.os == 'macOS' || runner.os == 'Windows' || (runner.os == 'Linux' && runner.arch != 'ARM64' && steps.check_python.outputs.installed == 'false' ) }}
name: Setup Python ${{ inputs.version }}
uses: actions/setup-python@v5
with:

View File

@ -54,26 +54,18 @@ NPU:
HETERO:
revalidate:
- CPU
- GPU
- HETERO
- AUTO_BATCH
- TEMPLATE
- C_API
- Python_API
build:
- TEMPLATE
- IR_FE
AUTO_BATCH:
revalidate:
- CPU
- GPU
- HETERO
- AUTO_BATCH
- TEMPLATE
- C_API
- Python_API
build:
- TEMPLATE
- IR_FE
TEMPLATE:
@ -91,11 +83,10 @@ TEMPLATE:
AUTO:
revalidate:
- TEMPLATE
- AUTO
- C_API
- Python_API
build:
- TEMPLATE
- IR_FE
PROXY:

View File

@ -1 +1 @@
pr-24449
pr-24878

View File

@ -29,6 +29,7 @@ RUN apt-get update && \
python3.11-dev \
python3.11-venv \
python3.11-distutils \
libhdf5-dev \
# For Java API
default-jdk \
# Compiler

View File

@ -0,0 +1,72 @@
FROM openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04
USER root
# APT configuration
RUN echo 'Acquire::Retries "10";' > /etc/apt/apt.conf && \
echo 'APT::Get::Assume-Yes "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::Fix-Broken "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::no-install-recommends "true";' >> /etc/apt/apt.conf
ENV DEBIAN_FRONTEND="noninteractive" \
TZ="Europe/London"
RUN apt-get update && \
apt-get install software-properties-common && \
add-apt-repository --yes --no-update ppa:git-core/ppa && \
add-apt-repository --yes --no-update ppa:deadsnakes/ppa && \
apt-get update && \
apt-get install \
curl \
git \
ca-certificates \
gpg-agent \
tzdata \
# Pythons
python3.8-dev \
python3.8-venv \
python3.8-distutils \
python3.11-dev \
python3.11-venv \
python3.11-distutils \
# For Java API
default-jdk \
# Compiler \
gcc-10 \
g++-10 \
&& \
rm -rf /var/lib/apt/lists/*
# Install build dependencies
ADD install_build_dependencies.sh /install_build_dependencies.sh
RUN chmod +x /install_build_dependencies.sh && \
/install_build_dependencies.sh && \
rm -rf /var/lib/apt/lists/*
# Set gcc-10 as a default compiler
RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-10 30 && \
update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-10 30
# Install sscache
ARG SCCACHE_VERSION="v0.7.5"
ENV SCCACHE_HOME="/opt/sccache" \
SCCACHE_PATH="/opt/sccache/sccache"
RUN mkdir ${SCCACHE_HOME} && cd ${SCCACHE_HOME} && \
SCCACHE_ARCHIVE="sccache-${SCCACHE_VERSION}-x86_64-unknown-linux-musl.tar.gz" && \
curl -SLO https://github.com/mozilla/sccache/releases/download/${SCCACHE_VERSION}/${SCCACHE_ARCHIVE} && \
tar -xzf ${SCCACHE_ARCHIVE} --strip-components=1 && rm ${SCCACHE_ARCHIVE}
# Setup pip
ENV PIP_VERSION="24.0"
RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
python3.8 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
python3.11 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
rm -f get-pip.py
# Use Python 3.11 as default instead of Python 3.8
# Using venv here 'cause other methods to switch the default Python on Ubuntu 20 break both system and wheels build
RUN python3.11 -m venv venv
ENV PATH="/venv/bin:$SCCACHE_HOME:$PATH"
ENV PIP_CACHE_DIR=/mount/caches/pip/linux/${PIP_VERSION}

View File

@ -0,0 +1,89 @@
FROM openvinogithubactions.azurecr.io/dockerhub/nvidia/cuda:11.8.0-runtime-ubuntu20.04
USER root
# APT configuration
RUN echo 'Acquire::Retries "10";' > /etc/apt/apt.conf && \
echo 'APT::Get::Assume-Yes "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::Fix-Broken "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::no-install-recommends "true";' >> /etc/apt/apt.conf
ENV DEBIAN_FRONTEND="noninteractive" \
TZ="Europe/London"
RUN apt-get update && \
apt-get install software-properties-common && \
add-apt-repository --yes --no-update ppa:git-core/ppa && \
add-apt-repository --yes --no-update ppa:deadsnakes/ppa && \
apt-get update && \
apt-get install \
curl \
wget \
git \
ca-certificates \
gpg-agent \
tzdata \
# Pythons
python3.8-dev \
python3.8-venv \
python3.8-distutils \
python3.11-dev \
python3.11-venv \
python3.11-distutils \
# For Java API
default-jdk \
# Compiler \
gcc-10 \
g++-10 \
&& \
rm -rf /var/lib/apt/lists/*
# Install build dependencies
ADD install_build_dependencies.sh /install_build_dependencies.sh
RUN chmod +x /install_build_dependencies.sh && \
/install_build_dependencies.sh && \
rm -rf /var/lib/apt/lists/*
# Set gcc-10 as a default compiler
RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-10 30 && \
update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-10 30
# Install sscache
ARG SCCACHE_VERSION="v0.7.5"
ENV SCCACHE_HOME="/opt/sccache" \
SCCACHE_PATH="/opt/sccache/sccache"
RUN mkdir ${SCCACHE_HOME} && cd ${SCCACHE_HOME} && \
SCCACHE_ARCHIVE="sccache-${SCCACHE_VERSION}-x86_64-unknown-linux-musl.tar.gz" && \
curl -SLO https://github.com/mozilla/sccache/releases/download/${SCCACHE_VERSION}/${SCCACHE_ARCHIVE} && \
tar -xzf ${SCCACHE_ARCHIVE} --strip-components=1 && rm ${SCCACHE_ARCHIVE}
# Install CUDA
RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin && \
mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600 && \
apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub && \
add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /"
RUN apt update && apt install -y \
libcudnn8=8.9.4.*-1+cuda11.8 \
libcudnn8-dev=8.9.4.*-1+cuda11.8 \
libcudnn8-samples=8.9.4.*-1+cuda11.8 \
cuda-runtime-11-8 \
cuda-11-8 \
libcutensor1=1.6.1.5-1 \
libcutensor-dev=1.6.1.5-1 \
cuda-drivers=520.61.05-1 && \
rm -rf /var/lib/apt/lists/*
# Setup pip
ENV PIP_VERSION="24.0"
RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
python3.8 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
python3.11 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
rm -f get-pip.py
# Use Python 3.11 as default instead of Python 3.8
# Using venv here 'cause other methods to switch the default Python on Ubuntu 20 break both system and wheels build
RUN python3.11 -m venv venv
ENV PATH="/venv/bin:$SCCACHE_HOME:$PATH"
ENV PIP_CACHE_DIR=/mount/caches/pip/linux/${PIP_VERSION}

View File

@ -0,0 +1,73 @@
FROM openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04
USER root
# APT configuration
RUN echo 'Acquire::Retries "10";' > /etc/apt/apt.conf && \
echo 'APT::Get::Assume-Yes "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::Fix-Broken "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::no-install-recommends "true";' >> /etc/apt/apt.conf
ENV DEBIAN_FRONTEND="noninteractive" \
TZ="Europe/London"
RUN apt-get update && \
apt-get install software-properties-common && \
add-apt-repository --yes --no-update ppa:git-core/ppa && \
add-apt-repository --yes --no-update ppa:deadsnakes/ppa && \
apt-get update && \
apt-get install \
curl \
git \
ca-certificates \
gpg-agent \
tzdata \
libtbb2 \
# Pythons
python3.8-dev \
python3.8-venv \
python3.8-distutils \
python3.11-dev \
python3.11-venv \
python3.11-distutils \
# For Java API
default-jdk \
# Compiler \
gcc-10 \
g++-10 \
&& \
rm -rf /var/lib/apt/lists/*
# Install build dependencies
ADD install_build_dependencies.sh /install_build_dependencies.sh
RUN chmod +x /install_build_dependencies.sh && \
/install_build_dependencies.sh && \
rm -rf /var/lib/apt/lists/*
# Set gcc-10 as a default compiler
RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-10 30 && \
update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-10 30
# Install sscache
ARG SCCACHE_VERSION="v0.7.5"
ENV SCCACHE_HOME="/opt/sccache" \
SCCACHE_PATH="/opt/sccache/sccache"
RUN mkdir ${SCCACHE_HOME} && cd ${SCCACHE_HOME} && \
SCCACHE_ARCHIVE="sccache-${SCCACHE_VERSION}-x86_64-unknown-linux-musl.tar.gz" && \
curl -SLO https://github.com/mozilla/sccache/releases/download/${SCCACHE_VERSION}/${SCCACHE_ARCHIVE} && \
tar -xzf ${SCCACHE_ARCHIVE} --strip-components=1 && rm ${SCCACHE_ARCHIVE}
# Setup pip
ENV PIP_VERSION="24.0"
RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
python3.8 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
python3.11 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
rm -f get-pip.py
# Use Python 3.11 as default instead of Python 3.8
# Using venv here 'cause other methods to switch the default Python on Ubuntu 20 break both system and wheels build
RUN python3.11 -m venv venv
ENV PATH="/venv/bin:$SCCACHE_HOME:$PATH"
ENV PIP_CACHE_DIR=/mount/caches/pip/linux/${PIP_VERSION}

View File

@ -0,0 +1,72 @@
FROM openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04
USER root
# APT configuration
RUN echo 'Acquire::Retries "10";' > /etc/apt/apt.conf && \
echo 'APT::Get::Assume-Yes "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::Fix-Broken "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::no-install-recommends "true";' >> /etc/apt/apt.conf
ENV DEBIAN_FRONTEND="noninteractive" \
TZ="Europe/London"
RUN apt-get update && \
apt-get install software-properties-common && \
add-apt-repository --yes --no-update ppa:git-core/ppa && \
add-apt-repository --yes --no-update ppa:deadsnakes/ppa && \
apt-get update && \
apt-get install \
curl \
git \
ca-certificates \
gpg-agent \
tzdata \
libtbb2 \
# Pythons
python3.8-dev \
python3.8-venv \
python3.8-distutils \
python3.11-dev \
python3.11-venv \
python3.11-distutils \
# For Java API
default-jdk \
# Compiler \
clang \
&& \
rm -rf /var/lib/apt/lists/*
# Install build dependencies
ADD install_build_dependencies.sh /install_build_dependencies.sh
RUN chmod +x /install_build_dependencies.sh && \
/install_build_dependencies.sh && \
rm -rf /var/lib/apt/lists/*
# Set clang as a default compiler
RUN update-alternatives --install /usr/bin/cc cc /usr/bin/clang 100 && \
update-alternatives --install /usr/bin/c++ c++ /usr/bin/clang++ 100
# Install sscache
ARG SCCACHE_VERSION="v0.7.5"
ENV SCCACHE_HOME="/opt/sccache" \
SCCACHE_PATH="/opt/sccache/sccache"
RUN mkdir ${SCCACHE_HOME} && cd ${SCCACHE_HOME} && \
SCCACHE_ARCHIVE="sccache-${SCCACHE_VERSION}-x86_64-unknown-linux-musl.tar.gz" && \
curl -SLO https://github.com/mozilla/sccache/releases/download/${SCCACHE_VERSION}/${SCCACHE_ARCHIVE} && \
tar -xzf ${SCCACHE_ARCHIVE} --strip-components=1 && rm ${SCCACHE_ARCHIVE}
# Setup pip
ENV PIP_VERSION="24.0"
RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
python3.8 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
python3.11 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
rm -f get-pip.py
# Use Python 3.11 as default instead of Python 3.8
# Using venv here 'cause other methods to switch the default Python on Ubuntu 20 break both system and wheels build
RUN python3.11 -m venv venv
ENV PATH="/venv/bin:$SCCACHE_HOME:$PATH"
ENV PIP_CACHE_DIR=/mount/caches/pip/linux/${PIP_VERSION}

View File

@ -26,6 +26,7 @@ RUN apt-get update && \
python3.11-dev \
python3.11-venv \
python3.11-distutils \
libhdf5-dev \
&& \
rm -rf /var/lib/apt/lists/*
@ -47,3 +48,4 @@ RUN python3.11 -m venv venv
ENV PATH="/venv/bin:$PATH"
ENV PIP_CACHE_DIR=/mount/caches/pip/linux/${PIP_VERSION}
ENV PIP_INSTALL_PATH=/venv/lib/python3.11/site-packages

View File

@ -0,0 +1,52 @@
FROM openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04
USER root
# APT configuration
RUN echo 'Acquire::Retries "10";' > /etc/apt/apt.conf && \
echo 'APT::Get::Assume-Yes "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::Fix-Broken "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::no-install-recommends "true";' >> /etc/apt/apt.conf
ENV DEBIAN_FRONTEND="noninteractive" \
TZ="Europe/London"
RUN apt-get update && \
apt-get install software-properties-common && \
add-apt-repository --yes --no-update ppa:git-core/ppa && \
add-apt-repository --yes --no-update ppa:deadsnakes/ppa && \
apt-get update && \
apt-get install \
curl \
git \
ca-certificates \
gpg-agent \
tzdata \
# Python
python3.11-dev \
python3.11-venv \
python3.11-distutils \
libhdf5-dev \
&& \
rm -rf /var/lib/apt/lists/*
# Install build dependencies
ADD install_build_dependencies.sh /install_build_dependencies.sh
RUN chmod +x /install_build_dependencies.sh && \
/install_build_dependencies.sh && \
rm -rf /var/lib/apt/lists/*
# Setup pip
ENV PIP_VERSION="24.0"
RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
python3.8 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
python3.11 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
rm -f get-pip.py
# Use Python 3.11 as default instead of Python 3.8
# Using venv here 'cause other methods to switch the default Python on Ubuntu 20 break both system and wheels build
RUN python3.11 -m venv venv
ENV PATH="/venv/bin:$SCCACHE_HOME:$PATH"
ENV PIP_CACHE_DIR=/mount/caches/pip/linux/${PIP_VERSION}
ENV PIP_INSTALL_PATH=/venv/lib/python3.11/site-packages

View File

@ -0,0 +1,52 @@
FROM openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04
USER root
# APT configuration
RUN echo 'Acquire::Retries "10";' > /etc/apt/apt.conf && \
echo 'APT::Get::Assume-Yes "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::Fix-Broken "true";' >> /etc/apt/apt.conf && \
echo 'APT::Get::no-install-recommends "true";' >> /etc/apt/apt.conf
ENV DEBIAN_FRONTEND="noninteractive" \
TZ="Europe/London"
RUN apt-get update && \
apt-get install software-properties-common && \
add-apt-repository --yes --no-update ppa:git-core/ppa && \
add-apt-repository --yes --no-update ppa:deadsnakes/ppa && \
apt-get update && \
apt-get install \
curl \
git \
ca-certificates \
gpg-agent \
tzdata \
# Python
python3.11-dev \
python3.11-venv \
python3.11-distutils \
libhdf5-dev \
&& \
rm -rf /var/lib/apt/lists/*
# Install build dependencies
ADD install_build_dependencies.sh /install_build_dependencies.sh
RUN chmod +x /install_build_dependencies.sh && \
/install_build_dependencies.sh && \
rm -rf /var/lib/apt/lists/*
# Setup pip
ENV PIP_VERSION="24.0"
RUN curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
python3 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
python3.11 get-pip.py --no-cache-dir pip==${PIP_VERSION} && \
rm -f get-pip.py
# Use Python 3.11 as default
# Using venv here 'cause other methods to switch the default Python on Ubuntu 20 break both system and wheels build
RUN python3.11 -m venv venv
ENV PATH="/venv/bin:$SCCACHE_HOME:$PATH"
ENV PIP_CACHE_DIR=/mount/caches/pip/linux/${PIP_VERSION}
ENV PIP_INSTALL_PATH=/venv/lib/python3.11/site-packages

View File

@ -50,5 +50,13 @@
{
"error_text": "The requested URL returned error: 500",
"ticket": 139384
},
{
"error_text": "Unable to fetch some archives",
"ticket": 130965
},
{
"error_text": "status_string: \"Timeout was reached\"",
"ticket": 142653
}
]

View File

@ -13,6 +13,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-android-arm64-vcpkg
cancel-in-progress: true
permissions: read-all
jobs:
Smart_CI:
runs-on: ubuntu-latest
@ -21,7 +23,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -75,7 +77,7 @@ jobs:
run: apt-get update && apt-get install --assume-yes --no-install-recommends git ca-certificates
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'
@ -90,7 +92,7 @@ jobs:
popd
- name: Clone vcpkg
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'microsoft/vcpkg'
# Keep in sync with <root>/vcpkg.json <builtin-baseline>
@ -130,7 +132,7 @@ jobs:
echo "yes" | ./cmdline-tools/bin/sdkmanager --sdk_root=${ANDROID_TOOLS} --install "ndk-bundle" "platform-tools" "platforms;android-${{ env.ANDROID_SDK_VERSION }}"
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
uses: mozilla-actions/sccache-action@2e7f9ec7921547d4b46598398ca573513895d0bd # v0.0.4
with:
version: "v0.7.5"
@ -182,7 +184,7 @@ jobs:
# Upload build logs
#
- name: Upload build logs
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: build_logs

View File

@ -6,6 +6,8 @@ on:
- created
- edited
permissions: read-all
jobs:
take-issue:
name: Take issue
@ -15,7 +17,7 @@ jobs:
timeout-minutes: 10
steps:
- name: take an issue
uses: bdougie/take-action@v1.6.1
uses: bdougie/take-action@1439165ac45a7461c2d89a59952cd7d941964b87 # v1.6.1
with:
message: Thank you for looking into this issue! Please let us know if you have any questions or require any help.
issueCurrentlyAssignedMessage: Thanks for being interested in this issue. It looks like this ticket is already assigned to a contributor. Please communicate with the assigned contributor to confirm the status of the issue.

View File

@ -10,23 +10,25 @@ concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
permissions: read-all
jobs:
Build_Doc:
runs-on: ubuntu-20.04
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
submodules: 'true'
lfs: 'true'
- name: Install apt-get dependencies
uses: awalsh128/cache-apt-pkgs-action@v1.4.2
uses: awalsh128/cache-apt-pkgs-action@a6c3917cc929dd0345bfb2d3feaf9101823370ad # v1.4.2
with:
packages: graphviz texlive liblua5.2-0 libclang1-9 libclang-cpp9
version: 3.0
- uses: actions/setup-python@v5
- uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
id: cp310
with:
python-version: '3.10'
@ -39,6 +41,7 @@ jobs:
run: |
python3 -m pip install -r docs/requirements.txt
(cd docs/openvino_sphinx_theme && python3 setup.py install)
python3 -m pip install docs/openvino_custom_sphinx_sitemap
- name: Download and install doxygen
run: |
@ -50,12 +53,12 @@ jobs:
- name: Build docs
run: |
rm -rf build && mkdir build && cd build
cmake .. -DCMAKE_BUILD_TYPE=Release -DENABLE_DOCS=ON -DENABLE_CPP_API=ON
cmake .. -DCMAKE_BUILD_TYPE=Release -DENABLE_DOCS=ON
cmake --build . --target sphinx_docs
- name: Cache documentation
id: cache_sphinx_docs
uses: actions/cache@v4
uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
with:
path: build/docs/_build/.doctrees
key: sphinx-docs-cache
@ -68,39 +71,31 @@ jobs:
PR_NUMBER=$(echo $GITHUB_REF | awk 'BEGIN { FS = "/" } ; { print $3 }')
echo "PR_NUMBER=$PR_NUMBER" >> $GITHUB_ENV
- name: 'Upload doxygen.log'
uses: actions/upload-artifact@v4
with:
name: doxygen_build_log_${{ env.PR_NUMBER }}.log
path: build/docs/doxygen.log
- name: 'Upload sphinx.log'
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: sphinx_build_log_${{ env.PR_NUMBER }}.log
path: build/docs/sphinx.log
- name: 'Upload docs html'
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_docs_html_${{ env.PR_NUMBER }}.zip
path: build/docs/openvino_docs_html.zip
- name: Run Pytest
run: |
pytest --doxygen="./build/docs/doxygen.log" \
--sphinx="./build/docs/sphinx.log" \
pytest --sphinx="./build/docs/sphinx.log" \
--suppress-warnings="./docs/scripts/tests/suppress_warnings.txt" \
--confcutdir="./docs/scripts/tests/" \
--html="./build/docs/_artifacts/doc-generation.html" \
--doxygen-strip="$(pwd)" \
--sphinx-strip="$(pwd)/build/docs/sphinx_source" \
--xfail="./docs/scripts/tests/xfail.txt" \
--self-contained-html ./docs/scripts/tests/test_docs.py
- name: 'Upload test results'
if: failure()
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_docs_pytest
path: build/docs/_artifacts/

View File

@ -1,12 +1,14 @@
name: PR Commits
on: [pull_request]
permissions: read-all
jobs:
Checks:
runs-on: ubuntu-22.04
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- name: Install dependencies
run: python3 -m pip install -r ./.github/github_org_control/requirements.txt

View File

@ -5,6 +5,8 @@ on:
# at 00:00 on the 1st day of every month
- cron: '0 0 1 * *'
permissions: read-all
jobs:
Cleanup_PIP:
runs-on: aks-linux-2-cores-8gb
@ -42,7 +44,7 @@ jobs:
steps:
- name: Checkout cach action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/cache

View File

@ -16,6 +16,8 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: read-all
jobs:
Build:
strategy:
@ -25,12 +27,12 @@ jobs:
runs-on: ${{ matrix.os }}
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
submodules: 'true'
- name: Install OpenCL
uses: awalsh128/cache-apt-pkgs-action@v1.4.2
uses: awalsh128/cache-apt-pkgs-action@a6c3917cc929dd0345bfb2d3feaf9101823370ad # v1.4.2
if: runner.os == 'Linux'
with:
packages: ocl-icd-opencl-dev opencl-headers

View File

@ -5,13 +5,15 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: read-all
jobs:
clang-format:
runs-on: ubuntu-22.04
permissions:
pull-requests: write
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
submodules: 'true'
@ -29,7 +31,7 @@ jobs:
- name: suggester / clang-format
if: startsWith(github.event_name, 'pull_request')
uses: reviewdog/action-suggester@v1
uses: reviewdog/action-suggester@9e1cd88b79ba3c0023c94e44accd72344f032093 # v1.13.0
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
level: warning
@ -40,7 +42,7 @@ jobs:
permissions:
pull-requests: write
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
submodules: 'true'
@ -58,7 +60,7 @@ jobs:
# always provide suggestions even for skipped scripts in ov_shellcheck tagret
- name: ShellCheck action
if: always()
uses: reviewdog/action-shellcheck@v1
uses: reviewdog/action-shellcheck@6e3a862f231c6895fbd335b70adef8f9243d5762 # v1.21.0
with:
level: style
reporter: github-pr-review
@ -71,7 +73,7 @@ jobs:
NamingConventionCheck:
runs-on: ubuntu-22.04
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
submodules: 'true'

View File

@ -5,6 +5,8 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: read-all
jobs:
Coverage:
runs-on: ${{ matrix.config.os }}
@ -16,19 +18,19 @@ jobs:
steps:
- name: Setup python
uses: actions/setup-python@v5
uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
with:
python-version: '3.10.10'
architecture: 'x64'
- name: Setup ccache
uses: hendrikmuhs/ccache-action@v1.2
uses: hendrikmuhs/ccache-action@c92f40bee50034e84c763e33b317c77adaa81c92 # v1.2.13
with:
max-size: 50G
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
submodules: 'true'
@ -55,7 +57,7 @@ jobs:
python3 -m pip install -r ${{ github.workspace }}/tools/mo/requirements_dev.txt
- name: Build OpenVINO with CMake
uses: ashutoshvarma/action-cmake-build@master
uses: ashutoshvarma/action-cmake-build@ade188313bc7eaa6f14349569a64d8bc716342ff # master
with:
build-dir: ${{ github.workspace }}/build
cc: ${{ matrix.config.cc }}
@ -112,7 +114,7 @@ jobs:
run: ${{ github.workspace }}/bin/intel64/Release/ov_tensorflow_frontend_tests --gtest_filter=-*IE_GPU*
- name: Build coverage with CMake
uses: ashutoshvarma/action-cmake-build@master
uses: ashutoshvarma/action-cmake-build@ade188313bc7eaa6f14349569a64d8bc716342ff # master
with:
build-dir: ${{ github.workspace }}/coverage
cc: ${{ matrix.config.cc }}
@ -135,6 +137,6 @@ jobs:
lcov --capture --directory ${{ github.workspace }}/. --output-file coverage.info
genhtml coverage.info --output-directory coverage-report
- name: Collect coverage
uses: codecov/codecov-action@v4
uses: codecov/codecov-action@125fc84a9a348dbcf27191600683ec096ec9021c # v4.4.1
with:
verbose: true

View File

@ -14,6 +14,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-linux-coverity
cancel-in-progress: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -44,14 +46,14 @@ jobs:
apt-get install --assume-yes --no-install-recommends git ca-certificates
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: ${{ env.OPENVINO_REPO }}
submodules: 'true'
ref: ${{ inputs.openvinoRef }}
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: ${{ env.OPENVINO_CONTRIB_REPO }}
@ -137,7 +139,7 @@ jobs:
run: ${COVERITY_TOOL_DIR}/cov-analysis*/bin/cov-configure -c ${COVERITY_TOOL_DIR}/cov-analysis-linux64-2023.6.2/config/coverity_config.xml -lscc text
- name: Upload Coverity build log
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: coverity_logs
@ -145,7 +147,7 @@ jobs:
if-no-files-found: 'error'
- name: Upload Coverity build archive
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: coverity_archive

View File

@ -1,18 +1,17 @@
name: 'Dependency Review'
on: [pull_request, merge_group]
permissions:
contents: read
permissions: read-all
jobs:
dependency-review:
runs-on: ubuntu-latest
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- name: Dependency Review
uses: actions/dependency-review-action@v4.3.2
uses: actions/dependency-review-action@72eb03d02c7872a771aacd928f3123ac62ad6d3a # v4.3.3
with:
config-file: './.github/dependency_review.yml'
base-ref: ${{ github.pull_request.base.sha || github.event.merge_group.base_ref }}

View File

@ -13,6 +13,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-fedora33
cancel-in-progress: true
permissions: read-all
jobs:
Smart_CI:
runs-on: ubuntu-latest
@ -21,7 +23,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -71,7 +73,7 @@ jobs:
run: yum update -y && yum install -y git
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: ${{ env.OPENVINO_REPO }}
submodules: 'true'
@ -91,7 +93,7 @@ jobs:
run: bash ${OPENVINO_REPO}/install_build_dependencies.sh
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
uses: mozilla-actions/sccache-action@2e7f9ec7921547d4b46598398ca573513895d0bd # v0.0.4
with:
version: "v0.7.5"
@ -125,7 +127,6 @@ jobs:
-DENABLE_NCC_STYLE=OFF \
-DENABLE_TESTS=ON \
-DENABLE_STRICT_DEPENDENCIES=OFF \
-DENABLE_SYSTEM_TBB=ON \
-DENABLE_SYSTEM_OPENCL=ON \
-DENABLE_PYTHON_PACKAGING=ON \
-DCPACK_GENERATOR=TGZ \
@ -160,7 +161,9 @@ jobs:
- name: Build RPM packages
run: |
cmake -DCPACK_GENERATOR=RPM \
cmake -UTBB* \
-DCPACK_GENERATOR=RPM \
-DENABLE_SYSTEM_TBB=ON \
-DENABLE_TESTS=OFF \
${BUILD_DIR}
cmake --build ${BUILD_DIR} --parallel --target package --verbose
@ -169,7 +172,7 @@ jobs:
# Upload build artifacts and logs
#
- name: Upload build logs
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: build_logs
@ -178,7 +181,7 @@ jobs:
- name: Upload openvino package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package
path: ${{ env.BUILD_DIR }}/openvino_package.tar.gz
@ -186,7 +189,7 @@ jobs:
- name: Upload openvino RPM packages
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_rpm_packages
path: ${{ env.BUILD_DIR }}/*.rpm
@ -194,7 +197,7 @@ jobs:
- name: Upload openvino tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.tar.gz
@ -214,7 +217,7 @@ jobs:
steps:
- name: Download OpenVINO RPM packages
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_rpm_packages
path: ${{ env.RPM_PACKAGES_DIR }}

View File

@ -5,11 +5,13 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: read-all
jobs:
Check_Files_Size:
runs-on: ubuntu-22.04
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- name: git ls-tree
run: git ls-tree -r -t -l --full-name HEAD | sort -n -r -k 4

View File

@ -13,6 +13,8 @@ on:
required: false
default: null
permissions: read-all
jobs:
CPU_Functional_Tests:
name: CPU functional tests
@ -30,18 +32,14 @@ jobs:
PARALLEL_TEST_SCRIPT: ${{ github.workspace }}/install/tests/functional_test_utils/layer_tests_summary/run_parallel.py
PARALLEL_TEST_CACHE: ${{ github.workspace }}/install/tests/test_cache.lst
steps:
- name: Set apt retries
if: runner.os == 'Linux'
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -64,12 +62,8 @@ jobs:
tar -xzf openvino_tests.tar.gz -C $INSTALL_DIR
popd
- name: Install OpenVINO dependencies (Linux)
if: runner.os == 'Linux'
run: $INSTALL_DIR/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -c=gpu -y
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -87,7 +81,7 @@ jobs:
run: python3 -m pip install -r ${INSTALL_TEST_DIR}/functional_test_utils/layer_tests_summary/requirements.txt
- name: Restore tests execution time
uses: actions/cache/restore@v4
uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
with:
path: ${{ env.PARALLEL_TEST_CACHE }}
key: ${{ runner.os }}-${{ runner.arch }}-tests-functional-cpu-stamp-${{ github.sha }}
@ -107,14 +101,14 @@ jobs:
timeout-minutes: 25
- name: Save tests execution time
uses: actions/cache/save@v4
uses: actions/cache/save@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
if: github.ref_name == 'master'
with:
path: ${{ env.PARALLEL_TEST_CACHE }}
key: ${{ runner.os }}-${{ runner.arch }}-tests-functional-cpu-stamp-${{ github.sha }}
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: test-results-functional-cpu

View File

@ -17,6 +17,8 @@ on:
type: string
required: true
permissions: read-all
jobs:
CXX_Unit_Tests:
name: C++ unit tests
@ -32,18 +34,14 @@ jobs:
INSTALL_DIR: ${{ github.workspace }}/install
INSTALL_TEST_DIR: ${{ github.workspace }}/install/tests
steps:
- name: Set apt retries
if: runner.os == 'Linux'
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -63,10 +61,6 @@ jobs:
tar -xzf openvino_tests.tar.gz -C $INSTALL_DIR
popd
- name: Install OpenVINO dependencies (Linux)
if: runner.os == 'Linux'
run: $INSTALL_DIR/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -c=gpu -y
#
# Tests
#
@ -162,6 +156,7 @@ jobs:
--gtest_output=xml:${INSTALL_TEST_DIR}/TEST-Transformations.xml
- name: Common test utils tests
if: ${{ runner.os != 'macOS' }} # Ticket: 134469
run: |
source ${INSTALL_DIR}/setupvars.sh
${INSTALL_TEST_DIR}/ov_util_tests --gtest_print_time=1 \
@ -216,6 +211,7 @@ jobs:
--gtest_output=xml:${INSTALL_TEST_DIR}/TEST-TemplateFuncTests.xml
- name: OV utils unit tests
if: ${{ runner.os != 'macOS' }} # Ticket: 134469
run: |
source ${INSTALL_DIR}/setupvars.sh
${INSTALL_TEST_DIR}/ov_util_tests --gtest_print_time=1 \
@ -259,7 +255,7 @@ jobs:
${INSTALL_TEST_DIR}/ov_hetero_func_tests --gtest_print_time=1 --gtest_output=xml:${INSTALL_TEST_DIR}/TEST-OVHeteroFuncTests.xml --gtest_filter="*smoke*"
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-cpp

View File

@ -13,6 +13,8 @@ on:
required: false
default: null
permissions: read-all
jobs:
Debian_Packages:
name: Debian Packages
@ -31,7 +33,7 @@ jobs:
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO debian packages
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_debian_packages
path: ${{ env.DEBIAN_PACKAGES_DIR }}

134
.github/workflows/job_gpu_tests.yml vendored Normal file
View File

@ -0,0 +1,134 @@
name: GPU
on:
workflow_call:
inputs:
test_type:
description: 'Type of tests to execute'
type: string
required: true
device:
description: 'Device name (igpu or dgpu)'
type: string
required: true
runner:
description: 'Runner labels by which the runner will be chosen. Example: [ "self-hosted", "igpu" ]'
type: string
required: true
container:
description: 'JSON to be converted to the value of the "container" configuration for the job'
type: string
required: false
default: '{"image": null}'
jobs:
GPU:
timeout-minutes: 80
runs-on: ${{ fromJSON(inputs.runner) }}
container: ${{ fromJSON(inputs.container) }}
defaults:
run:
shell: bash
env:
DEBIAN_FRONTEND: noninteractive # to prevent apt-get from waiting user input
INSTALL_DIR: ${{ github.workspace }}/install
INSTALL_TEST_DIR: ${{ github.workspace }}/install/tests
GTEST_PARALLEL_SCRIPT: ${{ github.workspace }}/gtest_parallel.py
steps:
- name: Download OpenVINO package
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: 'openvino_package'
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: 'openvino_tests'
path: ${{ env.INSTALL_TEST_DIR }}
# Needed as ${{ github.workspace }} is not working correctly when using Docker
- name: Setup Variables
run: |
echo "INSTALL_DIR=$GITHUB_WORKSPACE/install" >> "$GITHUB_ENV"
echo "INSTALL_TEST_DIR=$GITHUB_WORKSPACE/install/tests" >> "$GITHUB_ENV"
echo "GTEST_PARALLEL_SCRIPT=$GITHUB_WORKSPACE/gtest_parallel.py" >> "$GITHUB_ENV"
- name: Extract OpenVINO packages
run: |
pushd $INSTALL_DIR
tar -xzf openvino_package.tar.gz -C $INSTALL_DIR
popd
pushd $INSTALL_TEST_DIR
tar -xzf openvino_tests.tar.gz -C $INSTALL_DIR
popd
- name: Install dependencies (Linux)
run: |
$INSTALL_DIR/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -c=gpu -y
apt-get update && apt-get install -y wget software-properties-common ca-certificates gpg-agent tzdata clinfo
env:
DEBIAN_FRONTEND: noninteractive # to prevent apt-get from waiting user input
TZ: "Europe/London" # to prevent tzdata from waiting user input
- name: Setup Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
with:
python-version: ${{ env.PYTHON_VERSION }}
- name: Get gtest-parallel script
run: wget https://raw.githubusercontent.com/google/gtest-parallel/master/gtest_parallel.py
- name: Install compute runtime drivers
run: |
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.15985.7/intel-igc-core_1.0.15985.7_amd64.deb
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.15985.7/intel-igc-opencl_1.0.15985.7_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-level-zero-gpu-dbgsym_1.3.28454.6_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-level-zero-gpu_1.3.28454.6_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-opencl-icd-dbgsym_24.05.28454.6_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-opencl-icd_24.05.28454.6_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/libigdgmm12_22.3.11_amd64.deb
dpkg -i *.deb
- name: Install media & display runtimes
if: ${{ inputs.device == 'dgpu' }}
run: |
apt-get update && apt-get install -y \
libegl-mesa0 libegl1-mesa libegl1-mesa-dev libgbm1 libgl1-mesa-dev libgl1-mesa-dri \
libglapi-mesa libgles2-mesa-dev libglx-mesa0 libigdgmm11 libxatracker2 mesa-va-drivers \
mesa-vdpau-drivers mesa-vulkan-drivers va-driver-all
- name: Verify devices
run: clinfo
#
# Tests
#
- name: OpenVINO GPU ${{ inputs.test_type }} Tests
id: run_tests
run: |
source ${INSTALL_DIR}/setupvars.sh
TEST_RESULTS_DIR="${{ inputs.device }}_${{ inputs.test_type }}_tests"
echo "test_results_dir=$TEST_RESULTS_DIR" >> $GITHUB_OUTPUT
rm -rf ${INSTALL_TEST_DIR}/${TEST_RESULTS_DIR} && mkdir -p ${INSTALL_TEST_DIR}/${TEST_RESULTS_DIR}
test_filter=''
if [[ "${{ inputs.test_type }}" == "unit" ]]; then
# Ticket: 138018
test_filter='-*scatter_nd_update_gpu.dynamic_padded_output*:*border_gpu.basic_zero_input*:*bicubic_zeros_no_align_data1x1*:*bicubic_border_align_batches*:*bilinear_zeros_no_align_data1x1*:*non_zero_gpu.empty_input*:*mark_shape_of_subgraphs.concat_with_empty_tensor_inputs*:*concat_cpu_impl.dynamic_4d_f*:*border_gpu.basic_zero_input_dynamic*:*network_test.model_with_empty_input_is_not_dynamic*:*bicubic_zeros_align_data1x1*'
else
test_filter='*smoke*'
fi
python3 ${GTEST_PARALLEL_SCRIPT} ${INSTALL_TEST_DIR}/ov_gpu_${{ inputs.test_type }}_tests --dump_json_test_results=${INSTALL_TEST_DIR}/${TEST_RESULTS_DIR}/ov_gpu_${{ inputs.test_type }}_tests.json -- --report_unique_name --gtest_filter=$test_filter
- name: Upload Test Results
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: test-results-${{ inputs.test_type }}-${{ inputs.device }}
path: ${{ env.INSTALL_TEST_DIR }}/${{ steps.run_tests.outputs.test_results_dir }}
if-no-files-found: 'error'

View File

@ -13,6 +13,8 @@ on:
required: false
default: '{"image": null}'
permissions: read-all
jobs:
ONNX_Models_tests:
name: ONNX Models tests
@ -35,18 +37,14 @@ jobs:
ONNX_MODEL_ZOO_SHA: "5faef4c33eba0395177850e1e31c4a6a9e634c82"
if: ${{ github.event_name != 'merge_group' }}
steps:
- name: Set apt retries
if: runner.os == 'Linux'
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -70,27 +68,14 @@ jobs:
tar -xzf openvino_tests.tar.gz -C ${INSTALL_DIR}
popd
- name: Fetch setup_python action and model_zoo_preprocess script
uses: actions/checkout@v4
- name: Fetch model_zoo_preprocess script
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
src/frontends/onnx/tests/tests_python/model_zoo_preprocess.sh
sparse-checkout-cone-mode: false
path: 'openvino'
- name: Install dependencies
run: |
# install git (required to build pip deps from the sources)
apt-get update && apt-get install --assume-yes --no-install-recommends git ca-certificates git-lfs
- name: Setup Python 3.11
uses: ./openvino/.github/actions/setup_python
with:
version: '3.11'
should-setup-pip-paths: 'false'
self-hosted-runner: ${{ contains(inputs.runner, 'aks') }}
- name: Update Models
run: bash ${OPENVINO_REPO}/src/frontends/onnx/tests/tests_python/model_zoo_preprocess.sh -d ${MODELS_SHARE_PATH} -o -s "${{ env.ONNX_MODEL_ZOO_SHA }}"

View File

@ -17,6 +17,8 @@ on:
type: string
required: true
permissions: read-all
jobs:
ONNX_Runtime:
name: ONNX Runtime Integration
@ -40,12 +42,8 @@ jobs:
ONNX_RUNTIME_UTILS: ${{ github.workspace }}/install/onnxruntime
ONNX_RUNTIME_BUILD_DIR: ${{ github.workspace }}/onnxruntime/build
steps:
- name: Set apt retries
if: runner.os == 'Linux'
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
@ -59,38 +57,12 @@ jobs:
echo "ONNX_RUNTIME_UTILS=$GITHUB_WORKSPACE/install/onnxruntime" >> "$GITHUB_ENV"
echo "ONNX_RUNTIME_BUILD_DIR=$GITHUB_WORKSPACE/onnxruntime/build" >> "$GITHUB_ENV"
- name: Fetch install_build_dependencies.sh and setup_python action
uses: actions/checkout@v4
with:
sparse-checkout: |
install_build_dependencies.sh
.github/actions/setup_python/action.yml
sparse-checkout-cone-mode: false
path: 'openvino'
- name: Install git
run: |
apt-get update
apt-get install --assume-yes --no-install-recommends git ca-certificates
- name: Setup Python ${{ env.PYTHON_VERSION }}
uses: ./openvino/.github/actions/setup_python
with:
version: '3.11'
should-setup-pip-paths: 'false'
- name: Extract OpenVINO package
run: |
pushd ${INSTALL_DIR}
tar -xzf openvino_package.tar.gz -C ${INSTALL_DIR}
popd
- name: Install OpenVINO dependencies
run: |
${INSTALL_DIR}/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -y
# since we are on Ubuntu 22.04, but compiled OpenVINO on Ubuntu 20.04, we need to install `libtbb2`
apt-get install --assume-yes --no-install-recommends libtbb2
- name: Clone ONNX Runtime
run: |
hash=`tr -s '\n ' < ${ONNX_RUNTIME_UTILS}/version`
@ -102,14 +74,6 @@ jobs:
# Tests
#
- name: Install Build Dependencies
run: bash ${OPENVINO_REPO}/install_build_dependencies.sh
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
with:
version: "v0.7.5"
- name: Build Lin ONNX Runtime
run: |
source ${INSTALL_DIR}/setupvars.sh
@ -133,7 +97,7 @@ jobs:
if: ${{ runner.arch != 'ARM64' }} # Ticket: 126277
run: |
# see https://github.com/microsoft/onnxruntime/issues/13197#issuecomment-1264542497
apt-get install --assume-yes --no-install-recommends language-pack-en
apt-get update && apt-get install --assume-yes --no-install-recommends language-pack-en
locale-gen en_US.UTF-8
update-locale LANG=en_US.UTF-8

View File

@ -13,6 +13,8 @@ on:
required: false
default: '{"image": null}'
permissions: read-all
jobs:
JS_API:
name: OpenVINO JS API
@ -29,7 +31,7 @@ jobs:
NODE_VERSION: 20
steps:
- name: Fetch OpenVINO JS sources
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
src/bindings/js
@ -42,13 +44,13 @@ jobs:
echo "OPENVINO_JS_LIBS_DIR=$GITHUB_WORKSPACE/openvino/src/bindings/js/node/bin" >> "$GITHUB_ENV"
- name: Download OpenVINO JS package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_js_package
path: ${{ env.OPENVINO_JS_LIBS_DIR }}
- name: Setup Node ${{ env.NODE_VERSION }}
uses: actions/setup-node@v4
uses: actions/setup-node@60edb5dd545a775178f52524783378180af0d1f8 # v4.0.2
with:
node-version: ${{ env.NODE_VERSION }}

View File

@ -17,6 +17,8 @@ on:
type: string
required: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -37,18 +39,15 @@ jobs:
INSTALL_TEST_DIR: ${{ github.workspace }}/install/tests
LAYER_TESTS_INSTALL_DIR: ${{ github.workspace }}/install/tests/layer_tests
steps:
- name: Set apt retries
if: runner.os == 'Linux'
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -70,12 +69,8 @@ jobs:
tar -xzf openvino_tests.tar.gz -C $INSTALL_DIR
popd
- name: Install OpenVINO dependencies (Linux)
if: runner.os == 'Linux'
run: $INSTALL_DIR/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -y -c=gpu
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -211,7 +206,7 @@ jobs:
python3 -m pytest ${LAYER_TESTS_INSTALL_DIR}/py_frontend_tests --junitxml=${INSTALL_TEST_DIR}/TEST-test_py_fontend.xml
- name: PyTorch Layer Tests
if: ${{ fromJSON(inputs.affected-components).PyTorch_FE.test && runner.arch != 'ARM64' }} # Ticket: 126287
if: ${{ fromJSON(inputs.affected-components).PyTorch_FE.test && runner.arch != 'ARM64' }} # Ticket: 126287, 142196
run: python3 -m pytest ${LAYER_TESTS_INSTALL_DIR}/pytorch_tests -n logical -m precommit --junitxml=${INSTALL_TEST_DIR}/TEST-pytorch.xml
env:
TEST_DEVICE: CPU
@ -275,7 +270,7 @@ jobs:
- name: Clone API snippets
if: runner.os != 'macOS'
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: docs/snippets
path: ${{ env.OPENVINO_REPO }}
@ -291,7 +286,7 @@ jobs:
python3 ${OPENVINO_REPO}/docs/snippets/main.py
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-python

View File

@ -17,6 +17,8 @@ on:
type: string
required: true
permissions: read-all
jobs:
PyTorch_Models_Tests:
name: PyTorch Models tests
@ -47,19 +49,19 @@ jobs:
fi
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tokenizers extension
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tokenizers_wheel
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -83,7 +85,7 @@ jobs:
popd
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -140,18 +142,29 @@ jobs:
USE_SYSTEM_CACHE: False
OP_REPORT_FILE: ${{ env.INSTALL_TEST_DIR }}/TEST-torch_unsupported_ops.log
- name: PagedAttention Test
if: always()
run: |
export PYTHONPATH=${MODEL_HUB_TESTS_INSTALL_DIR}:$PYTHONPATH
python3 -m pytest ${MODEL_HUB_TESTS_INSTALL_DIR}/pytorch/test_pa_transformation.py -m ${TYPE} --html=${INSTALL_TEST_DIR}/TEST-torch_pagedattention_tests.html --self-contained-html -v --tb=short
env:
TYPE: ${{ inputs.event == 'schedule' && 'nightly' || 'precommit'}}
TEST_DEVICE: CPU
USE_SYSTEM_CACHE: False
OP_REPORT_FILE: ${{ env.INSTALL_TEST_DIR }}/TEST-torch_unsupported_ops.log
- name: Reformat unsupported ops file
if: '!cancelled()'
run: |
python3 ${MODEL_HUB_TESTS_INSTALL_DIR}/pytorch/scripts/process_op_report.py ${INSTALL_TEST_DIR}/TEST-torch_unsupported_ops.log
- name: Available storage after tests
run: |
echo "Available storage:"
df -h
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-torch-models

View File

@ -17,6 +17,8 @@ on:
type: string
required: true
permissions: read-all
jobs:
Samples:
runs-on: ${{ inputs.runner }}
@ -31,18 +33,14 @@ jobs:
INSTALL_TEST_DIR: ${{ github.workspace }}/install/tests
BUILD_DIR: ${{ github.workspace }}/build
steps:
- name: Set apt retries
if: runner.os == 'Linux'
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -63,16 +61,12 @@ jobs:
tar -xzf openvino_tests.tar.gz -C $INSTALL_DIR
popd
- name: Install OpenVINO dependencies (Linux)
if: runner.os == 'Linux'
run: $INSTALL_DIR/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -y
- name: Install OpenVINO dependencies (mac)
if: runner.os == 'macOS'
run: brew install coreutils
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -84,7 +78,6 @@ jobs:
with:
version: '3.11'
should-setup-pip-paths: 'false'
self-hosted-runner: ${{ runner.os == 'Linux' }}
- name: Build cpp samples - GCC
run: $INSTALL_DIR/samples/cpp/build_samples.sh -i $INSTALL_DIR -b $BUILD_DIR/cpp_samples
@ -94,7 +87,7 @@ jobs:
- name: Build cpp samples - Clang
if: runner.os == 'Linux'
run: |
apt-get install -y clang
apt-get update && apt-get install -y clang
$INSTALL_DIR/samples/cpp/build_samples.sh -i $INSTALL_DIR -b $BUILD_DIR/cpp_samples_clang
env:
CMAKE_COMPILE_WARNING_AS_ERROR: 'ON'

View File

@ -21,6 +21,8 @@ on:
type: string
required: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -41,24 +43,20 @@ jobs:
INSTALL_TEST_DIR: ${{ github.workspace }}/install/tests
LAYER_TESTS_INSTALL_DIR: ${{ github.workspace }}/install/tests/layer_tests
steps:
- name: Set apt retries
if: runner.os == 'Linux'
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
- name: Download OpenVINO tokenizers extension
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tokenizers_wheel
path: ${{ env.INSTALL_DIR }}
@ -92,12 +90,8 @@ jobs:
Expand-Archive openvino_tests.zip -DestinationPath ${{ env.INSTALL_DIR }}
popd
- name: Install OpenVINO dependencies (Linux)
if: runner.os == 'Linux'
run: $INSTALL_DIR/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -y -c=gpu
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -164,7 +158,7 @@ jobs:
TEST_PRECISION: FP16
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-python-tf-layers

View File

@ -17,6 +17,8 @@ on:
type: string
required: true
permissions: read-all
jobs:
TensorFlow_Models_Tests:
name: TensorFlow Models tests
@ -34,33 +36,20 @@ jobs:
MODEL_HUB_TESTS_INSTALL_DIR: ${{ github.workspace }}/install/tests/model_hub_tests
NUMBER_OF_REPLICAS: 2
steps:
- name: Check sudo
if: ${{ runner.os == 'Linux' }}
run: if [ "$(id -u)" -eq 0 ]; then apt update && apt --assume-yes install sudo; fi
- name: Set apt retries
if: runner.os == 'Linux'
run: |
if [ "$(id -u)" -eq 0 ]; then
echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
else
sudo sh -c "echo 'Acquire::Retries \"10\";' >> /etc/apt/apt.conf.d/80-retries"
fi
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tokenizers extension
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tokenizers_wheel
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -88,19 +77,13 @@ jobs:
popd
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
sparse-checkout-cone-mode: false
path: 'openvino'
- name: Install dependencies
if: ${{ runner.os == 'Linux' }}
run: |
# install git (required to build pip deps from the sources)
sudo apt-get install --assume-yes --no-install-recommends g++ git ca-certificates wget
- name: Setup Python 3.11
uses: ./openvino/.github/actions/setup_python
with:
@ -131,7 +114,7 @@ jobs:
TEST_DEVICE: CPU
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-tensorflow-models-${{ inputs.model_scope }}

View File

@ -21,6 +21,8 @@ on:
type: string
required: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -48,7 +50,7 @@ jobs:
echo "EXTENSION_BUILD_DIR=$GITHUB_WORKSPACE/build" >> "$GITHUB_ENV"
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python
@ -64,14 +66,14 @@ jobs:
self-hosted-runner: ${{ runner.os == 'Linux' }}
- name: Clone OpenVINO Tokenizers
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_tokenizers'
path: ${{ env.OPENVINO_TOKENIZERS_REPO }}
ref: 'master'
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
@ -94,10 +96,6 @@ jobs:
# Dependencies
#
- name: Install build dependencies (Linux)
if: runner.os == 'Linux'
run: ./install_build_dependencies.sh
- name: Install python dependencies
run: |
# wheel packaging
@ -132,7 +130,7 @@ jobs:
- name: Upload openvino tokenizers wheel
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tokenizers_wheel
path: ${{ env.EXTENSION_BUILD_DIR }}/*.whl

View File

@ -2,6 +2,8 @@ name: "Pull Request Labeler"
on:
- pull_request_target
permissions: read-all
jobs:
triage:
permissions:
@ -9,20 +11,20 @@ jobs:
pull-requests: write
runs-on: ubuntu-latest
steps:
- uses: akladiev/labeler@v4.3.1
- uses: akladiev/labeler@eeac5941e7fb6f980d47e038ac0665168851c874 # v4.3.1
with:
repo-token: "${{ secrets.GITHUB_TOKEN }}"
configuration-path: '.github/labeler.yml'
sync-labels: 'true'
dot: 'true'
non-matching-label: 'no-match-files'
external_pr_labeller:
name: Label External PR
runs-on: ubuntu-latest
steps:
- name: Checkout Labeller Script
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: '.github'

View File

@ -16,6 +16,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-linux
cancel-in-progress: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -25,10 +27,11 @@ jobs:
runs-on: ubuntu-latest
outputs:
affected_components: "${{ steps.smart_ci.outputs.affected_components }}"
changed_components: "${{ steps.smart_ci.outputs.changed_components }}"
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -45,15 +48,44 @@ jobs:
skip_when_only_listed_labels_set: 'docs'
skip_when_only_listed_files_changed: '*.md,*.rst,*.png,*.jpg,*.svg'
Build:
- name: Show affected components
run: |
echo "${{ toJSON(steps.smart_ci.outputs.affected_components) }}"
shell: bash
Docker:
needs: Smart_CI
runs-on: aks-linux-4-cores-16gb-docker-build
container:
image: openvinogithubactions.azurecr.io/docker_build:0.2
volumes:
- /mount:/mount
outputs:
images: "${{ steps.handle_docker.outputs.images }}"
steps:
- name: Checkout
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- uses: ./.github/actions/handle_docker
id: handle_docker
with:
images: |
ov_build/ubuntu_20_04_x64
ov_build/ubuntu_20_04_x64_nvidia
ov_test/ubuntu_20_04_x64
registry: 'openvinogithubactions.azurecr.io'
dockerfiles_root_dir: '.github/dockerfiles'
changed_components: ${{ needs.smart_ci.outputs.changed_components }}
Build:
needs: [Docker, Smart_CI]
timeout-minutes: 150
defaults:
run:
shell: bash
runs-on: aks-linux-16-cores-32gb
container:
image: openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04
image: ${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}
volumes:
- /mount:/mount
options: -e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING
@ -80,22 +112,23 @@ jobs:
if: "!needs.smart_ci.outputs.skip_workflow"
steps:
- name: Set apt retries
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Install git
run: |
apt-get update
apt-get install --assume-yes --no-install-recommends git ca-certificates
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: ${{ env.OPENVINO_REPO }}
submodules: 'true'
# Ticket: 139627
- name: Checkout the latest OneDNN for GPU in nightly
if: ${{ github.event_name == 'schedule' }}
working-directory: ${{ env.OPENVINO_REPO }}/src/plugins/intel_gpu/thirdparty/onednn_gpu
run: |
git fetch origin
git checkout main
git rev-parse HEAD
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: ${{ env.OPENVINO_CONTRIB_REPO }}
@ -113,26 +146,6 @@ jobs:
# Dependencies
#
- name: Install build dependencies
run: |
bash ${OPENVINO_REPO}/install_build_dependencies.sh
# default-jdk - Java API
apt install --assume-yes --no-install-recommends default-jdk
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
with:
version: "v0.7.5"
- name: Setup Python ${{ env.PYTHON_VERSION }}
uses: ./openvino/.github/actions/setup_python
with:
version: ${{ env.PYTHON_VERSION }}
pip-cache-path: ${{ env.PIP_CACHE_PATH }}
should-setup-pip-paths: 'true'
self-hosted-runner: 'true'
show-cache-info: 'true'
- name: Install python dependencies
run: |
# For Python API: build and wheel packaging
@ -162,7 +175,6 @@ jobs:
-DENABLE_NCC_STYLE=OFF \
-DENABLE_TESTS=ON \
-DENABLE_STRICT_DEPENDENCIES=OFF \
-DENABLE_SYSTEM_TBB=ON \
-DENABLE_SYSTEM_OPENCL=ON \
-DCMAKE_VERBOSE_MAKEFILE=ON \
-DCPACK_GENERATOR=TGZ \
@ -213,6 +225,8 @@ jobs:
/usr/bin/python3.8 -m pip install -U pip
/usr/bin/python3.8 -m pip install -r ${OPENVINO_REPO}/src/bindings/python/wheel/requirements-dev.txt
cmake -UPYTHON* \
-UTBB* \
-DENABLE_SYSTEM_TBB=ON \
-DENABLE_PYTHON_PACKAGING=ON \
-DENABLE_TESTS=OFF \
-DPython3_EXECUTABLE=/usr/bin/python3.8 \
@ -242,7 +256,7 @@ jobs:
# Upload build artifacts and logs
#
- name: Upload build logs
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: build_logs
@ -251,7 +265,7 @@ jobs:
- name: Upload openvino package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package
path: ${{ env.BUILD_DIR }}/openvino_package.tar.gz
@ -259,7 +273,7 @@ jobs:
- name: Upload openvino js package
if: fromJSON(needs.smart_ci.outputs.affected_components).JS_API
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_js_package
path: ${{ env.INSTALL_DIR_JS }}
@ -267,7 +281,7 @@ jobs:
- name: Upload openvino developer package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_developer_package
path: ${{ env.BUILD_DIR }}/openvino_developer_package.tar.gz
@ -275,7 +289,7 @@ jobs:
- name: Upload openvino debian packages
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_debian_packages
path: ${{ env.BUILD_DIR }}/*.deb
@ -283,7 +297,7 @@ jobs:
- name: Upload openvino tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.tar.gz
@ -298,22 +312,22 @@ jobs:
image: 'openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04'
Samples:
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
if: fromJSON(needs.smart_ci.outputs.affected_components).samples
uses: ./.github/workflows/job_samples_tests.yml
with:
runner: 'aks-linux-4-cores-16gb'
image: 'openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04'
image: ${{ fromJSON(needs.docker.outputs.images).ov_test.ubuntu_20_04_x64 }}
affected-components: ${{ needs.smart_ci.outputs.affected_components }}
JS_API:
name: OpenVINO JS API
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
if: fromJSON(needs.smart_ci.outputs.affected_components).JS_API
uses: ./.github/workflows/job_openvino_js.yml
with:
runner: 'aks-linux-4-cores-16gb'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04"}'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}"}'
Conformance:
needs: [ Build, Smart_CI ]
@ -348,13 +362,13 @@ jobs:
#
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -369,7 +383,7 @@ jobs:
popd
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -413,7 +427,7 @@ jobs:
- name: Upload Conformance Artifacts
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: conformance_artifacts_${{ matrix.TEST_TYPE }}-${{ env.TEST_DEVICE }}
path: ${{ env.CONFORMANCE_ARTIFACTS_DIR }}/conformance_artifacts.tar.gz
@ -439,7 +453,7 @@ jobs:
- name: Upload Conformance Artifacts
if: ${{ matrix.TEST_TYPE == 'API' }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: conformance_artifacts_${{ matrix.TEST_TYPE }}-TEMPLATE
path: ${{ env.CONFORMANCE_ARTIFACTS_DIR }}/conformance_artifacts.tar.gz
@ -449,90 +463,90 @@ jobs:
name: ONNX Runtime Integration
if: fromJSON(needs.smart_ci.outputs.affected_components).ONNX_RT ||
fromJSON(needs.smart_ci.outputs.affected_components).ONNX_FE
needs: [ Build, Smart_CI ]
needs: [ Build, Smart_CI, Docker ]
uses: ./.github/workflows/job_onnx_runtime.yml
with:
runner: 'aks-linux-16-cores-32gb'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04", "volumes": ["/mount:/mount"], "options": "-e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING"}'
sccache-azure-key-prefix: 'ubuntu22_x86_64_onnxruntime'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"], "options": "-e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING"}'
sccache-azure-key-prefix: 'ubuntu20_x86_64_onnxruntime'
ONNX_Models:
name: ONNX Models Tests
if: fromJSON(needs.smart_ci.outputs.affected_components).Python_API.test ||
fromJSON(needs.smart_ci.outputs.affected_components).ONNX_FE.test
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
uses: ./.github/workflows/job_onnx_models_tests.yml
with:
runner: 'aks-linux-16-cores-32gb'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04", "volumes": ["/mount:/mount"]}'
runner: 'aks-linux-16-cores-64gb'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"]}'
CXX_Unit_Tests:
name: C++ unit tests
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
uses: ./.github/workflows/job_cxx_unit_tests.yml
with:
runner: 'aks-linux-4-cores-16gb'
image: 'openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04'
image: ${{ fromJSON(needs.docker.outputs.images).ov_test.ubuntu_20_04_x64 }}
affected-components: ${{ needs.smart_ci.outputs.affected_components }}
Python_Unit_Tests:
name: Python unit tests
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
uses: ./.github/workflows/job_python_unit_tests.yml
with:
runner: 'aks-linux-4-cores-16gb'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04", "volumes": ["/mount:/mount"]}'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"]}'
affected-components: ${{ needs.smart_ci.outputs.affected_components }}
TensorFlow_Layer_Tests:
name: TensorFlow Layer Tests
needs: [ Build, Smart_CI, Openvino_tokenizers ]
needs: [ Docker, Build, Smart_CI, Openvino_tokenizers ]
uses: ./.github/workflows/job_tensorflow_layer_tests.yml
with:
runner: 'aks-linux-4-cores-16gb'
shell: bash
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04", "volumes": ["/mount:/mount"]}'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"]}'
affected-components: ${{ needs.smart_ci.outputs.affected_components }}
CPU_Functional_Tests:
name: CPU functional tests
if: fromJSON(needs.smart_ci.outputs.affected_components).CPU.test
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
uses: ./.github/workflows/job_cpu_functional_tests.yml
with:
runner: 'aks-linux-8-cores-32gb'
image: 'openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04'
image: ${{ fromJSON(needs.docker.outputs.images).ov_test.ubuntu_20_04_x64 }}
TensorFlow_Models_Tests_Precommit:
name: TensorFlow Models tests
if: fromJSON(needs.smart_ci.outputs.affected_components).TF_FE.test ||
fromJSON(needs.smart_ci.outputs.affected_components).TFL_FE.test
needs: [ Build, Smart_CI, Openvino_tokenizers ]
needs: [ Docker, Build, Smart_CI, Openvino_tokenizers ]
uses: ./.github/workflows/job_tensorflow_models_tests.yml
with:
runner: 'aks-linux-8-cores-16gb'
model_scope: 'precommit'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04", "volumes": ["/mount:/mount"]}'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"]}'
TensorFlow_Models_Tests_Nightly_TF_HUB:
name: TensorFlow TF Hub Models tests
if: ${{ github.event_name == 'schedule' }}
needs: [ Build, Smart_CI, Openvino_tokenizers ]
needs: [ Docker, Build, Smart_CI, Openvino_tokenizers ]
uses: ./.github/workflows/job_tensorflow_models_tests.yml
with:
runner: 'aks-linux-8-cores-32gb'
runner: 'aks-linux-8-cores-64gb'
model_scope: 'nightly_tf_hub'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04", "volumes": ["/mount:/mount"]}'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"]}'
TensorFlow_Models_Tests_Nightly_HF:
name: TensorFlow Hugging Face Models tests
if: ${{ github.event_name == 'schedule' }}
needs: [ Build, Smart_CI, Openvino_tokenizers ]
needs: [ Docker, Build, Smart_CI, Openvino_tokenizers ]
uses: ./.github/workflows/job_tensorflow_models_tests.yml
with:
runner: 'aks-linux-8-cores-32gb'
runner: 'aks-linux-8-cores-64gb'
model_scope: 'nightly_hf'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04", "volumes": ["/mount:/mount"]}'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"]}'
# TODO: Switch back to self-hosted runners
# container:
@ -550,14 +564,14 @@ jobs:
NVIDIA_Plugin:
name: NVIDIA plugin
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
timeout-minutes: 15
defaults:
run:
shell: bash
runs-on: aks-linux-16-cores-32gb
container:
image: openvinogithubactions.azurecr.io/dockerhub/nvidia/cuda:11.8.0-runtime-ubuntu20.04
image: ${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64_nvidia }}
volumes:
- /mount:/mount
options: -e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING
@ -581,28 +595,14 @@ jobs:
if: fromJSON(needs.smart_ci.outputs.affected_components).NVIDIA
steps:
- name: Set apt retries
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Fetch install_build_dependencies.sh
uses: actions/checkout@v4
with:
sparse-checkout: |
install_build_dependencies.sh
sparse-checkout-cone-mode: false
path: ${{ env.OPENVINO_REPO }}
- name: Install Prerequisites
run: apt update && apt install -y git ca-certificates
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO Developer package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_developer_package
path: ${{ env.INSTALL_DIR }}
@ -618,44 +618,12 @@ jobs:
popd
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: ${{ env.OPENVINO_CONTRIB_REPO }}
ref: 'master'
#
# Dependencies
#
- name: Install build dependencies
run: |
${OPENVINO_REPO}/install_build_dependencies.sh
apt -y --no-install-recommends install software-properties-common curl
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
with:
version: "v0.7.5"
- name: Install CUDA
run: |
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /"
apt update
apt install -y \
libcudnn8=8.9.4.*-1+cuda11.8 \
libcudnn8-dev=8.9.4.*-1+cuda11.8 \
libcudnn8-samples=8.9.4.*-1+cuda11.8 \
cuda-runtime-11-8 \
cuda-11-8 \
libcutensor1=1.6.1.5-1 \
libcutensor-dev=1.6.1.5-1 \
cuda-drivers=520.61.05-1
#
# Build
#
@ -675,128 +643,53 @@ jobs:
Openvino_tokenizers:
name: OpenVINO tokenizers extension
needs: [ Build, Smart_CI ]
needs: [ Build, Smart_CI, Docker ]
uses: ./.github/workflows/job_tokenizers.yml
with:
runner: 'aks-linux-4-cores-16gb'
shell: bash
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:20.04", "volumes": ["/mount:/mount"]}'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_x64 }}", "volumes": ["/mount:/mount"]}'
affected-components: ${{ needs.smart_ci.outputs.affected_components }}
if: fromJSON(needs.smart_ci.outputs.affected_components).TOKENIZERS
GPU:
name: GPU ${{ matrix.TEST_TYPE }} Tests
iGPU:
name: iGPU Tests
needs: [ Build, Smart_CI ]
if: fromJSON(needs.smart_ci.outputs.affected_components).GPU
timeout-minutes: 80
runs-on: [ self-hosted, gpu ]
uses: ./.github/workflows/job_gpu_tests.yml
strategy:
max-parallel: 2
fail-fast: false
matrix:
TEST_TYPE: ['unit', 'func']
container:
image: ubuntu:20.04
options: --device /dev/dri:/dev/dri --group-add 109 --group-add 44
volumes:
- /dev/dri:/dev/dri
defaults:
run:
shell: bash
env:
DEBIAN_FRONTEND: noninteractive # to prevent apt-get from waiting user input
INSTALL_DIR: ${{ github.workspace }}/install
INSTALL_TEST_DIR: ${{ github.workspace }}/install/tests
GTEST_PARALLEL_SCRIPT: ${{ github.workspace }}/gtest_parallel.py
steps:
- name: Download OpenVINO package
uses: actions/download-artifact@v4
with:
name: 'openvino_package'
path: ${{ env.INSTALL_DIR }}
with:
device: 'igpu'
test_type: ${{ matrix.TEST_TYPE }}
runner: "[ 'self-hosted', 'igpu' ]"
container: '{"image": "ubuntu:20.04", "volumes": ["/dev/dri:/dev/dri"], "options": "--group-add 109 --group-add 44
--device /dev/dri:/dev/dri"}'
if: fromJSON(needs.smart_ci.outputs.affected_components).GPU
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
with:
name: 'openvino_tests'
path: ${{ env.INSTALL_TEST_DIR }}
# Needed as ${{ github.workspace }} is not working correctly when using Docker
- name: Setup Variables
run: |
echo "INSTALL_DIR=$GITHUB_WORKSPACE/install" >> "$GITHUB_ENV"
echo "INSTALL_TEST_DIR=$GITHUB_WORKSPACE/install/tests" >> "$GITHUB_ENV"
echo "GTEST_PARALLEL_SCRIPT=$GITHUB_WORKSPACE/gtest_parallel.py" >> "$GITHUB_ENV"
- name: Extract OpenVINO packages
run: |
pushd $INSTALL_DIR
tar -xzf openvino_package.tar.gz -C $INSTALL_DIR
popd
pushd $INSTALL_TEST_DIR
tar -xzf openvino_tests.tar.gz -C $INSTALL_DIR
popd
- name: Install dependencies (Linux)
run: |
$INSTALL_DIR/install_dependencies/install_openvino_dependencies.sh -c=core -c=dev -c=gpu -y
apt-get update && apt-get install -y wget software-properties-common ca-certificates gpg-agent tzdata
env:
DEBIAN_FRONTEND: noninteractive # to prevent apt-get from waiting user input
TZ: "Europe/London" # to prevent tzdata from waiting user input
- name: Setup Python ${{ env.PYTHON_VERSION }}
uses: actions/setup-python@v5
with:
python-version: ${{ env.PYTHON_VERSION }}
- name: Get gtest-parallel script
run: wget https://raw.githubusercontent.com/google/gtest-parallel/master/gtest_parallel.py
- name: Install GPU Drivers
run: |
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.15985.7/intel-igc-core_1.0.15985.7_amd64.deb
wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.15985.7/intel-igc-opencl_1.0.15985.7_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-level-zero-gpu-dbgsym_1.3.28454.6_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-level-zero-gpu_1.3.28454.6_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-opencl-icd-dbgsym_24.05.28454.6_amd64.ddeb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/intel-opencl-icd_24.05.28454.6_amd64.deb
wget https://github.com/intel/compute-runtime/releases/download/24.05.28454.6/libigdgmm12_22.3.11_amd64.deb
dpkg -i *.deb
#
# Tests
#
- name: OpenVINO GPU ${{ matrix.TEST_TYPE }} Tests
run: |
source ${INSTALL_DIR}/setupvars.sh
rm -rf ${INSTALL_TEST_DIR}/gpu_${{ matrix.TEST_TYPE }}_tests && mkdir -p ${INSTALL_TEST_DIR}/gpu_${{ matrix.TEST_TYPE }}_tests
test_filter=''
if [[ "${{ matrix.TEST_TYPE }}" == "unit" ]]; then
# Ticket: 138018
test_filter='-*scatter_nd_update_gpu.dynamic_padded_output*:*border_gpu.basic_zero_input*:*bicubic_zeros_no_align_data1x1*:*bicubic_border_align_batches*:*bilinear_zeros_no_align_data1x1*:*non_zero_gpu.empty_input*:*mark_shape_of_subgraphs.concat_with_empty_tensor_inputs*:*concat_cpu_impl.dynamic_4d_f*:*border_gpu.basic_zero_input_dynamic*:*network_test.model_with_empty_input_is_not_dynamic*:*bicubic_zeros_align_data1x1*'
else
test_filter='*smoke*'
fi
python3 ${GTEST_PARALLEL_SCRIPT} ${INSTALL_TEST_DIR}/ov_gpu_${{ matrix.TEST_TYPE }}_tests --dump_json_test_results=${INSTALL_TEST_DIR}/gpu_${{ matrix.TEST_TYPE }}_tests/ov_gpu_${{ matrix.TEST_TYPE }}_tests.json -- --report_unique_name --gtest_filter=$test_filter
- name: Upload Test Results
uses: actions/upload-artifact@v4
if: always()
with:
name: test-results-${{ matrix.TEST_TYPE }}-gpu
path: ${{ env.INSTALL_TEST_DIR }}/gpu_${{ matrix.TEST_TYPE }}_tests
if-no-files-found: 'error'
dGPU:
name: dGPU Tests
needs: [ Build, Smart_CI ]
uses: ./.github/workflows/job_gpu_tests.yml
strategy:
max-parallel: 2
fail-fast: false
matrix:
TEST_TYPE: ['unit', 'func']
with:
device: 'dgpu'
test_type: ${{ matrix.TEST_TYPE }}
runner: "[ 'self-hosted', 'dgpu' ]"
container: '{"image": "ubuntu:20.04", "volumes": ["/dev/dri:/dev/dri"], "options": "--group-add 109 --group-add 44
--device /dev/dri/card0:/dev/dri/card0 --device /dev/dri/renderD128:/dev/dri/renderD128"}'
if: ${{ github.event_name == 'schedule' }}
Overall_Status:
name: ci/gha_overall_status
needs: [Smart_CI, Build, Debian_Packages, Samples, Conformance, ONNX_Runtime, CXX_Unit_Tests, Python_Unit_Tests, TensorFlow_Layer_Tests,
CPU_Functional_Tests, TensorFlow_Models_Tests_Precommit, PyTorch_Models_Tests, NVIDIA_Plugin, Openvino_tokenizers, GPU]
CPU_Functional_Tests, TensorFlow_Models_Tests_Precommit, PyTorch_Models_Tests, NVIDIA_Plugin, Openvino_tokenizers, iGPU]
if: ${{ always() }}
runs-on: ubuntu-latest
steps:

View File

@ -13,6 +13,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-linux-arm
cancel-in-progress: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -26,7 +28,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -59,7 +61,7 @@ jobs:
images: "${{ steps.handle_docker.outputs.images }}"
steps:
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- uses: ./.github/actions/handle_docker
id: handle_docker
@ -106,13 +108,13 @@ jobs:
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: ${{ env.OPENVINO_REPO }}
submodules: 'true'
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: ${{ env.OPENVINO_CONTRIB_REPO }}
@ -245,7 +247,7 @@ jobs:
# Upload build artifacts and logs
#
- name: Upload build logs
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: build_logs
@ -254,7 +256,7 @@ jobs:
- name: Upload openvino package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package
path: ${{ env.BUILD_DIR }}/openvino_package.tar.gz
@ -262,7 +264,7 @@ jobs:
- name: Upload openvino developer package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_developer_package
path: ${{ env.BUILD_DIR }}/openvino_developer_package.tar.gz
@ -270,7 +272,7 @@ jobs:
- name: Upload openvino js package
if: fromJSON(needs.smart_ci.outputs.affected_components).JS_API
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_js_package
path: ${{ env.INSTALL_DIR_JS }}
@ -278,7 +280,7 @@ jobs:
- name: Upload openvino debian packages
if: ${{ 'false' }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_debian_packages
path: ${{ env.BUILD_DIR }}/*.deb
@ -286,7 +288,7 @@ jobs:
- name: Upload openvino tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.tar.gz
@ -323,12 +325,12 @@ jobs:
name: ONNX Runtime Integration
if: fromJSON(needs.smart_ci.outputs.affected_components).ONNX_RT ||
fromJSON(needs.smart_ci.outputs.affected_components).ONNX_FE
needs: [ Build, Smart_CI ]
needs: [ Build, Smart_CI, Docker ]
uses: ./.github/workflows/job_onnx_runtime.yml
with:
runner: 'aks-linux-16-cores-arm'
container: '{"image": "openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04", "volumes": ["/mount:/mount"], "options": "-e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING"}'
sccache-azure-key-prefix: 'ubuntu22_aarch64_onnxruntime'
container: '{"image": "${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_20_04_arm64 }}", "volumes": ["/mount:/mount"], "options": "-e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING"}'
sccache-azure-key-prefix: 'ubuntu20_aarch64_onnxruntime'
Openvino_tokenizers:
name: OpenVINO tokenizers extension

View File

@ -13,6 +13,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-linux-cc
cancel-in-progress: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -22,10 +24,11 @@ jobs:
runs-on: ubuntu-latest
outputs:
affected_components: "${{ steps.smart_ci.outputs.affected_components }}"
changed_components: "${{ steps.smart_ci.outputs.changed_components }}"
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -42,15 +45,43 @@ jobs:
skip_when_only_listed_labels_set: 'docs'
skip_when_only_listed_files_changed: '*.md,*.rst,*.png,*.jpg,*.svg,*/layer_tests_summary/*,*/conformance/*'
Build:
- name: Show affected components
run: |
echo "${{ toJSON(steps.smart_ci.outputs.affected_components) }}"
shell: bash
Docker:
needs: Smart_CI
runs-on: aks-linux-4-cores-16gb-docker-build
container:
image: openvinogithubactions.azurecr.io/docker_build:0.2
volumes:
- /mount:/mount
outputs:
images: "${{ steps.handle_docker.outputs.images }}"
steps:
- name: Checkout
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- uses: ./.github/actions/handle_docker
id: handle_docker
with:
images: |
ov_build/ubuntu_22_04_x64_cc
ov_test/ubuntu_22_04_x64
registry: 'openvinogithubactions.azurecr.io'
dockerfiles_root_dir: '.github/dockerfiles'
changed_components: ${{ needs.smart_ci.outputs.changed_components }}
Build:
needs: [Docker, Smart_CI]
timeout-minutes: 150
defaults:
run:
shell: bash
runs-on: aks-linux-16-cores-32gb
container:
image: openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04
image: ${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_22_04_x64_cc }}
volumes:
- /mount:/mount
options: -e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING
@ -75,22 +106,14 @@ jobs:
if: ${{ !needs.smart_ci.outputs.skip_workflow && github.event_name != 'merge_group' }}
steps:
- name: Set apt retries
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Install git
run: |
apt-get update
apt-get install --assume-yes --no-install-recommends git ca-certificates git-lfs
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: ${{ env.OPENVINO_REPO }}
submodules: 'true'
- name: Clone test models
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/testdata'
path: ${{ env.MODELS_PATH }}
@ -104,32 +127,6 @@ jobs:
- name: System info
uses: ./openvino/.github/actions/system_info
#
# Dependencies
#
- name: Install build dependencies
run: |
bash ${OPENVINO_REPO}/install_build_dependencies.sh
# use clang as a default compiler
apt --assume-yes install clang
update-alternatives --install /usr/bin/cc cc /usr/bin/clang 100
update-alternatives --install /usr/bin/c++ c++ /usr/bin/clang++ 100
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
with:
version: "v0.7.5"
- name: Setup Python ${{ env.PYTHON_VERSION }}
uses: ./openvino/.github/actions/setup_python
with:
version: ${{ env.PYTHON_VERSION }}
pip-cache-path: ${{ env.PIP_CACHE_PATH }}
should-setup-pip-paths: 'true'
self-hosted-runner: 'true'
- name: Install python dependencies
run: |
# For running ONNX frontend unit tests
@ -208,11 +205,14 @@ jobs:
install_dependencies/install_openvino_dependencies.sh
popd
cp -v ${OPENVINO_REPO}/temp/tbb/lib/lib* ${INSTALL_TEST_DIR}/tests
pushd ${INSTALL_TEST_DIR}
tar -czvf ${BUILD_DIR}/openvino_tests.tar.gz \
tests/ov_cpu_func_tests \
tests/libopenvino_template_extension.so \
tests/libze_loader.so* \
tests/libhwloc* \
tests/libtbb* \
tests/functional_test_utils/layer_tests_summary/*
popd
@ -220,7 +220,7 @@ jobs:
# Upload build artifacts and logs
#
- name: Upload build logs
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: always()
with:
name: build_logs
@ -229,7 +229,7 @@ jobs:
- name: Upload openvino package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package
path: ${{ env.BUILD_DIR }}/openvino_package.tar.gz
@ -237,7 +237,7 @@ jobs:
- name: Upload selective build statistics package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_selective_build_stat
path: ${{ env.BUILD_DIR }}/openvino_selective_build_stat.tar.gz
@ -245,7 +245,7 @@ jobs:
- name: Upload OpenVINO tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.tar.gz
@ -253,14 +253,14 @@ jobs:
CC_Build:
name: Conditional Compilation
needs: Build
needs: [Build, Docker]
timeout-minutes: 20
defaults:
run:
shell: bash
runs-on: aks-linux-16-cores-32gb
container:
image: openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04
image: ${{ fromJSON(needs.docker.outputs.images).ov_build.ubuntu_22_04_x64_cc }}
volumes:
- /mount:/mount
options: -e SCCACHE_AZURE_BLOB_CONTAINER -e SCCACHE_AZURE_CONNECTION_STRING
@ -278,20 +278,14 @@ jobs:
SCCACHE_AZURE_KEY_PREFIX: ubuntu22_x86_64_cc_Release
steps:
- name: Set apt retries
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Install git
run: apt-get update && apt-get install --assume-yes --no-install-recommends git ca-certificates git-lfs
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: ${{ env.OPENVINO_REPO }}
submodules: 'true'
- name: Clone test models
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/testdata'
path: ${{ env.MODELS_PATH }}
@ -299,7 +293,7 @@ jobs:
ref: 'master'
- name: Download selective build statistics package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_selective_build_stat
path: ${{ env.SELECTIVE_BUILD_STAT_DIR }}
@ -308,17 +302,6 @@ jobs:
run: tar -xvzf ${SELECTIVE_BUILD_STAT_DIR}/openvino_selective_build_stat.tar.gz -C ${SELECTIVE_BUILD_STAT_DIR}
#
# Dependencies
#
- name: Install build dependencies
run: bash ${OPENVINO_REPO}/install_build_dependencies.sh
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
with:
version: "v0.7.5"
#
# Build
#
@ -353,11 +336,11 @@ jobs:
CPU_Functional_Tests:
name: CPU functional tests
if: fromJSON(needs.smart_ci.outputs.affected_components).CPU.test
needs: [ Build, Smart_CI ]
needs: [ Docker, Build, Smart_CI ]
uses: ./.github/workflows/job_cpu_functional_tests.yml
with:
runner: 'aks-linux-8-cores-32gb'
image: 'openvinogithubactions.azurecr.io/dockerhub/ubuntu:22.04'
image: ${{ fromJSON(needs.docker.outputs.images).ov_test.ubuntu_22_04_x64 }}
Overall_Status:
name: ci/gha_overall_status_linux_cc

View File

@ -16,6 +16,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-linux-riscv
cancel-in-progress: true
permissions: read-all
jobs:
Smart_CI:
runs-on: ubuntu-latest
@ -24,7 +26,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -75,7 +77,7 @@ jobs:
run: apt-get update && apt-get install --assume-yes --no-install-recommends git ca-certificates
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'

View File

@ -11,6 +11,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-linux-sanitizers
cancel-in-progress: true
permissions: read-all
env:
PIP_CACHE_PATH: /mount/caches/pip/linux
PYTHON_VERSION: '3.11'
@ -62,13 +64,13 @@ jobs:
apt-get install --assume-yes --no-install-recommends git ca-certificates
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: ${{ env.OPENVINO_REPO }}
submodules: 'true'
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: ${{ env.OPENVINO_CONTRIB_REPO }}
@ -184,7 +186,7 @@ jobs:
- name: Upload openvino package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package_${{ matrix.SANITIZER }}
path: ${{ env.BUILD_DIR }}/openvino_package.tar.gz
@ -192,7 +194,7 @@ jobs:
- name: Upload openvino tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests_${{ matrix.SANITIZER }}
path: ${{ env.BUILD_DIR }}/openvino_tests.tar.gz
@ -228,13 +230,13 @@ jobs:
run: echo 'Acquire::Retries "10";' > /etc/apt/apt.conf.d/80-retries
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: ${{ format('openvino_package_{0}', matrix.SANITIZER) }}
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: ${{ format('openvino_tests_{0}', matrix.SANITIZER) }}
path: ${{ env.INSTALL_TEST_DIR }}
@ -264,7 +266,7 @@ jobs:
apt update && apt --assume-yes install clang lld
- name: Fetch Sanitizer Suppression Lists
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
tests/lsan/suppressions.txt
@ -401,7 +403,7 @@ jobs:
--gtest_output=xml:${INSTALL_TEST_DIR}/TEST-OpImplTests.xml
- name: AUTO unit tests
if: ${{ 'false' }} # Ticket: 134423
if: always()
run: |
source ${INSTALL_DIR}/setupvars.sh
${INSTALL_TEST_DIR}/ov_auto_unit_tests --gtest_print_time=1 \
@ -460,7 +462,7 @@ jobs:
${INSTALL_TEST_DIR}/ov_hetero_func_tests --gtest_print_time=1 --gtest_output=xml:${INSTALL_TEST_DIR}/TEST-OVHeteroFuncTests.xml --gtest_filter="*smoke*"
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-cpp

View File

@ -29,11 +29,12 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-mac-main
cancel-in-progress: true
permissions: read-all
env:
PYTHON_VERSION: '3.11'
jobs:
Smart_CI:
runs-on: ubuntu-latest
outputs:
@ -41,7 +42,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -79,13 +80,13 @@ jobs:
BUILD_DIR: ${{ github.workspace }}/build
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'
submodules: 'true'
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: 'openvino_contrib'
@ -130,7 +131,7 @@ jobs:
#
- name: Setup ccache
uses: hendrikmuhs/ccache-action@v1.2
uses: hendrikmuhs/ccache-action@c92f40bee50034e84c763e33b317c77adaa81c92 # v1.2.13
with:
max-size: "2000M"
# Should save cache only if run in the master branch of the base repo
@ -203,7 +204,7 @@ jobs:
- name: Upload openvino package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package
path: ${{ env.BUILD_DIR }}/openvino_package.tar.gz
@ -211,7 +212,7 @@ jobs:
- name: Upload openvino tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.tar.gz
@ -219,7 +220,7 @@ jobs:
- name: Upload openvino js package
if: fromJSON(needs.smart_ci.outputs.affected_components).JS_API
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_js_package
path: ${{ env.INSTALL_DIR_JS }}

View File

@ -29,6 +29,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-mac-arm64
cancel-in-progress: true
permissions: read-all
env:
PYTHON_VERSION: '3.11'
@ -40,7 +42,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -78,13 +80,13 @@ jobs:
BUILD_DIR: ${{ github.workspace }}/build
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'
submodules: 'true'
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: 'openvino_contrib'
@ -129,7 +131,7 @@ jobs:
#
- name: Setup ccache
uses: hendrikmuhs/ccache-action@v1.2
uses: hendrikmuhs/ccache-action@c92f40bee50034e84c763e33b317c77adaa81c92 # v1.2.13
with:
max-size: "2000M"
# Should save cache only if run in the master branch of the base repo
@ -180,7 +182,7 @@ jobs:
run: |
cmake \
-DCUSTOM_OPERATIONS="calculate_grid;complex_mul;fft;grid_sample;sparse_conv;sparse_conv_transpose" \
-DOPENVINO_EXTRA_MODULES=${{ OPENVINO_CONTRIB_REPO }}/modules/custom_operations \
-DOPENVINO_EXTRA_MODULES=${{ env.OPENVINO_CONTRIB_REPO }}/modules/custom_operations \
-S ${{ env.OPENVINO_REPO }} \
-B ${{ env.BUILD_DIR }}
cmake --build ${{ env.BUILD_DIR }} --parallel --config ${{ env.CMAKE_BUILD_TYPE }}
@ -202,7 +204,7 @@ jobs:
- name: Upload openvino package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package
path: ${{ env.BUILD_DIR }}/openvino_package.tar.gz
@ -210,7 +212,7 @@ jobs:
- name: Upload openvino tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.tar.gz
@ -218,7 +220,7 @@ jobs:
- name: Upload openvino js package
if: fromJSON(needs.smart_ci.outputs.affected_components).JS_API
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_js_package
path: ${{ env.INSTALL_DIR_JS }}

View File

@ -16,20 +16,22 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: read-all
jobs:
Pylint-UT:
runs-on: ubuntu-22.04
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- name: Setup Python
uses: actions/setup-python@v5
uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
with:
python-version: '3.10'
- name: Cache pip
uses: actions/cache@v4
uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
with:
path: ~/.cache/pip
key: ${{ runner.os }}-pip-${{ hashFiles('tools/mo/requirements*.txt') }}
@ -53,4 +55,4 @@ jobs:
- name: Pylint-MO
run: pylint -d C,R,W openvino/tools/mo
working-directory: tools/mo
working-directory: tools/mo

View File

@ -11,20 +11,22 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: read-all
jobs:
Pylint-UT:
runs-on: ubuntu-22.04
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- name: Setup Python
uses: actions/setup-python@v5
uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
with:
python-version: '3.10'
- name: Cache pip
uses: actions/cache@v4
uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
with:
path: ~/.cache/pip
key: ${{ runner.os }}-pip-${{ hashFiles('src/bindings/python/requirements*.txt') }}

View File

@ -20,15 +20,17 @@ concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions: read-all
jobs:
linters:
runs-on: ubuntu-20.04
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
- name: Setup Python
uses: actions/setup-python@v5
uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
with:
python-version: '3.8'
@ -47,7 +49,7 @@ jobs:
git diff > samples_diff.diff
working-directory: samples/python
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: failure()
with:
name: samples_diff
@ -65,7 +67,7 @@ jobs:
git diff > pyopenvino_diff.diff
working-directory: src/bindings/python/src/openvino
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: failure()
with:
name: pyopenvino_diff
@ -83,7 +85,7 @@ jobs:
git diff > wheel_diff.diff
working-directory: src/bindings/python/wheel
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: failure()
with:
name: wheel_diff
@ -111,4 +113,3 @@ jobs:
fi
fi
done

View File

@ -35,7 +35,7 @@ jobs:
steps:
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: '.github'

View File

@ -4,15 +4,16 @@ on:
schedule:
- cron: '0 0 * * *'
permissions:
issues: write
pull-requests: write
permissions: read-all
jobs:
stale:
permissions:
issues: write
pull-requests: write
runs-on: ubuntu-latest
steps:
- uses: actions/stale@v9
- uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e # v9.0.0
with:
stale-issue-message: 'This issue will be closed in a week because of 9 months of no activity.'
stale-pr-message: 'This PR will be closed in a week because of 2 weeks of no activity.'

View File

@ -13,6 +13,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-webassembly
cancel-in-progress: true
permissions: read-all
jobs:
Smart_CI:
runs-on: ubuntu-latest
@ -21,7 +23,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -64,13 +66,13 @@ jobs:
run: apt-get update && apt-get install --assume-yes --no-install-recommends git ca-certificates
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'
submodules: 'true'
- name: Install sccache
uses: mozilla-actions/sccache-action@v0.0.4
uses: mozilla-actions/sccache-action@2e7f9ec7921547d4b46598398ca573513895d0bd # v0.0.4
with:
version: "v0.7.5"

View File

@ -16,6 +16,8 @@ env:
PIP_CACHE_PATH: /mount/caches/pip/win
PYTHON_VERSION: '3.11'
permissions: read-all
jobs:
Smart_CI:
runs-on: ubuntu-latest
@ -24,7 +26,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -67,13 +69,13 @@ jobs:
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'
submodules: 'true'
- name: Clone OpenVINO Contrib
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/openvino_contrib'
path: 'openvino_contrib'
@ -150,7 +152,9 @@ jobs:
${{ runner.os }}-${{ runner.arch }}-ccache
- name: Configure Developer Command Prompt for Microsoft Visual C++
uses: ilammy/msvc-dev-cmd@v1
uses: ilammy/msvc-dev-cmd@0b201ec74fa43914dc39ae48a89fd1d8cb592756 # v1.13.0
with:
toolset: 14.40
- name: Set SSL_CERT_FILE for model downloading for unit tests
run: echo SSL_CERT_FILE=$(python3 -m certifi) >> $env:GITHUB_ENV
@ -215,14 +219,14 @@ jobs:
#
- name: Upload openvino package
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_package
path: ${{ env.BUILD_DIR }}/openvino_package.zip
if-no-files-found: 'error'
- name: Upload openvino tests package
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.zip
@ -230,7 +234,7 @@ jobs:
- name: Upload openvino js package
if: fromJSON(needs.smart_ci.outputs.affected_components).JS_API
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_js_package
path: ${{ env.INSTALL_DIR_JS }}
@ -253,13 +257,13 @@ jobs:
steps:
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -274,7 +278,7 @@ jobs:
popd
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -339,22 +343,22 @@ jobs:
steps:
- name: Fetch OpenVINO JS sources
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
src/bindings/js
path: 'openvino'
- name: Download OpenVINO js package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_js_package
path: ${{ env.OPENVINO_JS_LIBS_DIR }}
- name: Setup Node
uses: actions/setup-node@v4
uses: actions/setup-node@60edb5dd545a775178f52524783378180af0d1f8 # v4.0.2
with:
node-version: 18
node-version: 20
- name: Configure OpenVINO JS
working-directory: ${{ env.OPENVINO_JS_DIR }}/node
@ -369,6 +373,15 @@ jobs:
working-directory: ${{ env.OPENVINO_JS_DIR }}/node
run: call npm test
- name: Create package dir
working-directory: ${{ env.OPENVINO_JS_DIR }}
run: mkdir project-uses-openvino-node
- name: Test installation of openvino-node package
working-directory: ${{ env.OPENVINO_JS_DIR }}/project-uses-openvino-node
run: |
npm i openvino-node
node -e "const { addon: ov } = require('openvino-node'); console.log(ov);"
Openvino_tokenizers:
name: OpenVINO tokenizers extension
needs: [ Build, Smart_CI ]
@ -396,13 +409,13 @@ jobs:
steps:
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -417,7 +430,7 @@ jobs:
popd
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -554,7 +567,7 @@ jobs:
run: python3 -m pytest -s ${{ env.INSTALL_TEST_DIR }}/ovc/unit_tests --junitxml=${{ env.INSTALL_TEST_DIR }}/TEST-OpenVinoConversion.xml
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-python
@ -584,13 +597,13 @@ jobs:
steps:
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -760,7 +773,7 @@ jobs:
${{ env.INSTALL_TEST_DIR }}/ov_hetero_func_tests --gtest_print_time=1 --gtest_output=xml:${{ env.INSTALL_TEST_DIR }}/TEST-OVHeteroFuncTests.xml --gtest_filter="*smoke*"
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-cpp
@ -784,13 +797,13 @@ jobs:
if: fromJSON(needs.smart_ci.outputs.affected_components).CPU.test
steps:
- name: Download OpenVINO package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_package
path: ${{ env.INSTALL_DIR }}
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -805,7 +818,7 @@ jobs:
popd
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -823,7 +836,7 @@ jobs:
run: python3 -m pip install -r ${{ github.workspace }}\install\tests\functional_test_utils\layer_tests_summary\requirements.txt
- name: Restore tests execution time
uses: actions/cache/restore@v4
uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
with:
path: ${{ env.PARALLEL_TEST_CACHE }}
key: ${{ runner.os }}-tests-functional-cpu-stamp-${{ github.sha }}
@ -837,14 +850,14 @@ jobs:
timeout-minutes: 60
- name: Save tests execution time
uses: actions/cache/save@v4
uses: actions/cache/save@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
if: github.ref_name == 'master'
with:
path: ${{ env.PARALLEL_TEST_CACHE }}
key: ${{ runner.os }}-tests-functional-cpu-stamp-${{ github.sha }}
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-functional-cpu

View File

@ -16,6 +16,8 @@ concurrency:
group: ${{ github.event_name == 'push' && github.run_id || github.ref }}-windows-cc
cancel-in-progress: true
permissions: read-all
env:
PYTHON_VERSION: '3.11'
@ -27,7 +29,7 @@ jobs:
skip_workflow: "${{ steps.smart_ci.outputs.skip_workflow }}"
steps:
- name: checkout action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: .github/actions/smart-ci
@ -50,7 +52,7 @@ jobs:
defaults:
run:
shell: pwsh
runs-on: aks-win-8-cores-64gb
runs-on: aks-win-32-cores-128gb
env:
CMAKE_BUILD_TYPE: 'Release'
CMAKE_GENERATOR: 'Ninja Multi-Config'
@ -70,13 +72,13 @@ jobs:
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'
submodules: 'true'
- name: Clone test models
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/testdata'
path: 'testdata'
@ -149,7 +151,9 @@ jobs:
${{ runner.os }}-${{ runner.arch }}-ccache
- name: Configure Developer Command Prompt for Microsoft Visual C++
uses: ilammy/msvc-dev-cmd@v1
uses: ilammy/msvc-dev-cmd@0b201ec74fa43914dc39ae48a89fd1d8cb592756 # v1.13.0
with:
toolset: 14.40
- name: Set SSL_CERT_FILE for model downloading for unit tests
run: echo SSL_CERT_FILE=$(python3 -m certifi) >> $env:GITHUB_ENV
@ -172,10 +176,11 @@ jobs:
- name: Clean ccache stats
run: '& ccache --zero-stats'
# If the build fails due to running out of RAM, please decrease the number of parallel jobs (--parallel n)
- name: Cmake build - CC COLLECT
run: |
cmake --build ${{ env.BUILD_DIR }} --parallel 8 --config ${{ env.CMAKE_BUILD_TYPE }} && `
cmake --build ${{ env.BUILD_DIR }} --parallel 8 --config ${{ env.CMAKE_BUILD_TYPE }} --target sea_itt_lib
cmake --build ${{ env.BUILD_DIR }} --parallel 16 --config ${{ env.CMAKE_BUILD_TYPE }} && `
cmake --build ${{ env.BUILD_DIR }} --parallel 16 --config ${{ env.CMAKE_BUILD_TYPE }} --target sea_itt_lib
- name: Show ccache stats
run: '& ccache --show-stats'
@ -242,7 +247,7 @@ jobs:
- name: Upload selective build statistics package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_selective_build_stat
path: ${{ env.BUILD_DIR }}/openvino_selective_build_stat.zip
@ -250,7 +255,7 @@ jobs:
- name: Upload OpenVINO tests package
if: ${{ always() }}
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
with:
name: openvino_tests
path: ${{ env.BUILD_DIR }}/openvino_tests.zip
@ -262,7 +267,7 @@ jobs:
defaults:
run:
shell: pwsh
runs-on: aks-win-8-cores-64gb
runs-on: aks-win-32-cores-128gb
env:
CMAKE_BUILD_TYPE: 'Release'
OPENVINO_REPO: "${{ github.workspace }}\\openvino"
@ -273,13 +278,13 @@ jobs:
steps:
- name: Clone OpenVINO
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
path: 'openvino'
submodules: 'true'
- name: Clone test models
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
repository: 'openvinotoolkit/testdata'
path: 'testdata'
@ -287,7 +292,7 @@ jobs:
ref: 'master'
- name: Download selective build statistics package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_selective_build_stat
path: ${{ env.SELECTIVE_BUILD_STAT_DIR }}
@ -349,7 +354,7 @@ jobs:
steps:
- name: Download OpenVINO tests package
uses: actions/download-artifact@v4
uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
with:
name: openvino_tests
path: ${{ env.INSTALL_TEST_DIR }}
@ -358,7 +363,7 @@ jobs:
run: Expand-Archive ${{ env.INSTALL_TEST_DIR }}/openvino_tests.zip -DestinationPath "${{ env.INSTALL_TEST_DIR }}"
- name: Fetch setup_python action
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: |
.github/actions/setup_python/action.yml
@ -376,7 +381,7 @@ jobs:
run: python3 -m pip install -r ${{ env.INSTALL_TEST_DIR }}/layer_tests_summary/requirements.txt
- name: Restore tests execution time
uses: actions/cache/restore@v4
uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # v4.0.2
with:
path: ${{ env.PARALLEL_TEST_CACHE }}
key: ${{ runner.os }}-tests-functional-cpu-stamp-${{ github.sha }}
@ -391,7 +396,7 @@ jobs:
timeout-minutes: 60
- name: Upload Test Results
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4.3.3
if: ${{ !cancelled() }}
with:
name: test-results-functional-cpu

View File

@ -16,6 +16,8 @@ on:
- '.github/workflows/workflow_rerunner.yml'
- '.github/scripts/workflow_rerun/**'
permissions: read-all
jobs:
rerun:
name: Rerun Workflow
@ -28,7 +30,7 @@ jobs:
checks: read
steps:
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: '.github/scripts/workflow_rerun'
@ -59,7 +61,7 @@ jobs:
runs-on: aks-linux-2-cores-8gb
steps:
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
with:
sparse-checkout: '.github/scripts/workflow_rerun'
lfs: true

View File

@ -71,7 +71,7 @@ if(OV_GENERATOR_MULTI_CONFIG)
string(REPLACE ";" " " config_types "${CMAKE_CONFIGURATION_TYPES}")
message (STATUS "CMAKE_CONFIGURATION_TYPES ............. " ${config_types})
unset(config_types)
if(CMAKE_GENERATOR MATCHES "^Ninja Multi-Config$")
if(CMAKE_GENERATOR STREQUAL "Ninja Multi-Config")
message (STATUS "CMAKE_DEFAULT_BUILD_TYPE .............. " ${CMAKE_DEFAULT_BUILD_TYPE})
endif()
else()

View File

@ -135,18 +135,18 @@ function(ov_download_tbb)
elseif(LINUX AND AARCH64 AND OPENVINO_GNU_LIBC AND OV_LIBC_VERSION VERSION_GREATER_EQUAL 2.17)
# build oneTBB 2021.2.1 with gcc 4.8 (glibc 2.17)
RESOLVE_DEPENDENCY(TBB
ARCHIVE_LIN "oneapi-tbb-2021.2.1-lin-arm64-20231012.tgz"
ARCHIVE_LIN "oneapi-tbb-2021.2.5-lin-arm64.tgz"
TARGET_PATH "${TEMP}/tbb"
ENVIRONMENT "TBBROOT"
SHA256 "cbb239cbda7ea2937cec7008c12fe628dd44488e1eafd9630f8814f9eb2c13e2"
SHA256 "86b24e4db254136bf88f0a8195ae478494e34db109e08569b1c059b174494865"
USE_NEW_LOCATION TRUE)
elseif(APPLE AND AARCH64)
# build oneTBB 2021.2.1 with export MACOSX_DEPLOYMENT_TARGET=11.0
RESOLVE_DEPENDENCY(TBB
ARCHIVE_MAC "oneapi-tbb-2021.2.4-mac-arm64.tgz"
ARCHIVE_MAC "oneapi-tbb-2021.2.5-mac-arm64.tgz"
TARGET_PATH "${TEMP}/tbb"
ENVIRONMENT "TBBROOT"
SHA256 "5e4581b95648d1c5d8f0742badecf48a9529feab6bc55ac94b526eddaf6a18c9"
SHA256 "bb1f84b1dcc50787f35c99b4b6ecea733d3068ca3467b5ebd2e369c4f7eccb53"
USE_NEW_LOCATION TRUE)
else()
message(WARNING "Prebuilt TBB is not available on current platform")

View File

@ -111,8 +111,8 @@ if(DEFINED SANITIZER_COMPILER_FLAGS)
# https://stackoverflow.com/questions/68571138/asan-dynamic-runtime-is-missing-on-ubuntu-18, https://bugs.llvm.org/show_bug.cgi?id=51271
if(BUILD_SHARED_LIBS AND ENABLE_SANITIZER AND OV_COMPILER_IS_CLANG)
execute_process(COMMAND ${CMAKE_CXX_COMPILER} --print-file-name libclang_rt.asan-x86_64.so
OUTPUT_VARIABLE LIBASAN_DIRNAME)
get_filename_component(LIBASAN_DIRNAME ${LIBASAN_DIRNAME} PATH)
OUTPUT_VARIABLE OV_LIBASAN_FILEPATH)
get_filename_component(LIBASAN_DIRNAME ${OV_LIBASAN_FILEPATH} PATH)
set(SANITIZER_LINKER_FLAGS "${SANITIZER_LINKER_FLAGS},-rpath=${LIBASAN_DIRNAME}")
endif()

View File

@ -226,11 +226,3 @@ function(ov_coverage_merge)
add_dependencies(ov_coverage_${OV_COVERAGE_OUTPUT}_info ${dependencies})
endfunction()
# deprecated
if(NOT TARGET ie_coverage)
add_custom_target(ie_coverage)
set_target_properties(ie_coverage PROPERTIES FOLDER coverage)
add_dependencies(ie_coverage ov_coverage)
endif()

View File

@ -81,7 +81,8 @@ function(cross_compiled_file TARGET)
## that is arch ID
set(_arch ${_it})
if(_arch MATCHES ${_CURRENT_ARCH_FILTER})
list(APPEND _CUR_ARCH_SET ${_arch})
# make non/less-optimized version coming first
list(INSERT _CUR_ARCH_SET 0 ${_arch})
list(APPEND _FULL_ARCH_SET ${_arch})
endif()
else()

View File

@ -71,7 +71,7 @@ function(ov_native_compile_external_project)
endif()
if(OV_GENERATOR_MULTI_CONFIG)
if(CMAKE_GENERATOR MATCHES "^Ninja Multi-Config$")
if(CMAKE_GENERATOR STREQUAL "Ninja Multi-Config")
list(APPEND ARG_CMAKE_ARGS "-DCMAKE_CONFIGURATION_TYPES=${CMAKE_DEFAULT_BUILD_TYPE}")
list(APPEND ARG_CMAKE_ARGS "-DCMAKE_DEFAULT_BUILD_TYPE=${CMAKE_DEFAULT_BUILD_TYPE}")
endif()

View File

@ -1,6 +1,6 @@
# custom OpenVINO values
CppMethod: '^(operator\W+|[a-z_\d]+|signaling_NaN|quiet_NaN|OPENVINO_OP)$'
ClassName: '^([A-Z][\w]+|b?float16|float8_e4m3|float8_e5m2|numeric_limits|ngraph_error|stopwatch|unsupported_op)$'
ClassName: '^([A-Z][\w]+|b?float16|float8_e4m3|float8_e5m2|float4_e2m1|numeric_limits|ngraph_error|stopwatch|unsupported_op)$'
StructName: '^([A-Z][\w]+|element_type_traits|hash|oi_pair|stat)$'
FunctionName: '^(operator\W+|[a-z_\d]+)|PrintTo$'
Namespace: '^([a-z\d_]*|InferenceEngine)$'
@ -18,7 +18,7 @@ VariableReference: '^\w+$'
EnumName: '^[A-Z][\w]+$'
# excepts element_type
EnumConstantName: '^([A-Z\d_]+|undefined|dynamic|boolean|bf16|f16|f32|f64|i4|i8|i16|i32|i64|u1|u2|u3|u4|u6|u8|u16|u32|u64|nf4|f8e4m3|f8e5m2|string|asymmetric|align_corners|round_prefer_floor|round_prefer_ceil|floor|ceil|simple|nearest|linear|linear_onnx|cubic|area|scales|sizes|half_pixel|tf_half_pixel_for_nn|pytorch_half_pixel|asymetric)$'
EnumConstantName: '^([A-Z\d_]+|undefined|dynamic|boolean|bf16|f16|f32|f64|i4|i8|i16|i32|i64|u1|u2|u3|u4|u6|u8|u16|u32|u64|nf4|f8e4m3|f8e5m2|f4e2m1|string|asymmetric|align_corners|round_prefer_floor|round_prefer_ceil|floor|ceil|simple|nearest|linear|linear_onnx|cubic|area|scales|sizes|half_pixel|tf_half_pixel_for_nn|pytorch_half_pixel|asymetric)$'
# TODO: align
UsingDeclaration: '^.*$'
TypedefName: '^.*$'

View File

@ -11,13 +11,11 @@ endif()
macro(ov_option variable description value)
option(${variable} "${description}" ${value})
list(APPEND OV_OPTIONS ${variable})
list(APPEND IE_OPTIONS ${variable})
endmacro()
macro(ov_dependent_option variable description def_value condition fallback_value)
cmake_dependent_option(${variable} "${description}" ${def_value} "${condition}" ${fallback_value})
list(APPEND OV_OPTIONS ${variable})
list(APPEND IE_OPTIONS ${variable})
endmacro()
macro(ov_option_enum variable description value)
@ -31,7 +29,6 @@ macro(ov_option_enum variable description value)
endif()
list(APPEND OV_OPTIONS ${variable})
list(APPEND IE_OPTIONS ${variable})
set(${variable} ${value} CACHE STRING "${description}")
set_property(CACHE ${variable} PROPERTY STRINGS ${OPTION_ENUM_ALLOWED_VALUES})

View File

@ -125,7 +125,7 @@ endif()\n")
# detect where OPENVINO_EXTRA_MODULES contains folders with CMakeLists.txt
# other folders are supposed to have sub-folders with CMakeLists.txt
foreach(module_path IN LISTS OPENVINO_EXTRA_MODULES IE_EXTRA_MODULES)
foreach(module_path IN LISTS OPENVINO_EXTRA_MODULES)
get_filename_component(module_path "${module_path}" ABSOLUTE)
if(EXISTS "${module_path}/CMakeLists.txt")
list(APPEND extra_modules "${module_path}")

View File

@ -162,11 +162,11 @@ else()
set(ENABLE_SYSTEM_FLATBUFFERS_DEFAULT ON)
endif()
# users wants to use his own TBB version, specific either via env vars or cmake options
if(DEFINED ENV{TBBROOT} OR DEFINED ENV{TBB_DIR} OR DEFINED TBB_DIR OR DEFINED TBBROOT)
set(ENABLE_SYSTEM_TBB_DEFAULT OFF)
else()
# use system TBB only for Debian / RPM packages
if(CPACK_GENERATOR MATCHES "^(DEB|RPM|CONDA-FORGE|BREW|CONAN|VCPKG)$")
set(ENABLE_SYSTEM_TBB_DEFAULT ${ENABLE_SYSTEM_LIBS_DEFAULT})
else()
set(ENABLE_SYSTEM_TBB_DEFAULT OFF)
endif()
ov_dependent_option (ENABLE_SYSTEM_TBB "Enables use of system TBB" ${ENABLE_SYSTEM_TBB_DEFAULT}

View File

@ -93,6 +93,7 @@ macro(ov_cpack_settings)
2023.3.0 2023.3.1 2023.3.2 2023.3.3 2023.3.4 2023.3.5
2024.0.0
2024.1.0
2024.2.0
)
ov_check_conflicts_versions(conflicting_versions)

View File

@ -81,6 +81,7 @@ macro(ov_cpack_settings)
2023.3.0 2023.3.1 2023.3.2 2023.3.3 2023.3.4 2023.3.5
2024.0.0
2024.1.0
2024.2.0
)
ov_check_conflicts_versions(conflicting_versions)

View File

@ -92,9 +92,16 @@
# `OpenVINO_VERSION_PATCH`
# Patch version component
#
# OpenVINO build configuration variables:
#
# `OpenVINO_GLIBCXX_USE_CXX11_ABI`
# Linux only: defines _GLIBCXX_USE_CXX11_ABI used to compiled OpenVINO
#
@PACKAGE_INIT@
set(OpenVINO_GLIBCXX_USE_CXX11_ABI "@OV_GLIBCXX_USE_CXX11_ABI@")
#
# Common functions
#
@ -473,6 +480,11 @@ set(_OV_ENABLE_OPENVINO_BUILD_SHARED "@BUILD_SHARED_LIBS@")
if(NOT TARGET openvino)
set(_ov_as_external_package ON)
include("${CMAKE_CURRENT_LIST_DIR}/OpenVINOTargets.cmake")
# since OpenVINO is compiled with _GLIBCXX_USE_CXX11_ABI=0
if(NOT OpenVINO_GLIBCXX_USE_CXX11_ABI STREQUAL "")
add_definitions(-D_GLIBCXX_USE_CXX11_ABI=${OpenVINO_GLIBCXX_USE_CXX11_ABI})
endif()
endif()
if(NOT _OV_ENABLE_OPENVINO_BUILD_SHARED)

View File

@ -22,7 +22,7 @@ endif()
get_property(_OV_GENERATOR_MULTI_CONFIG GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
if(_OV_GENERATOR_MULTI_CONFIG)
list(APPEND ov_options CMAKE_CONFIGURATION_TYPES)
if(CMAKE_GENERATOR MATCHES "^Ninja Multi-Config$")
if(CMAKE_GENERATOR STREQUAL "Ninja Multi-Config")
list(APPEND ov_options CMAKE_DEFAULT_BUILD_TYPE)
endif()
else()

View File

@ -18,7 +18,7 @@ endif()
get_property(_OV_GENERATOR_MULTI_CONFIG GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
if(_OV_GENERATOR_MULTI_CONFIG)
list(APPEND ov_options CMAKE_CONFIGURATION_TYPES)
if(CMAKE_GENERATOR MATCHES "^Ninja Multi-Config$")
if(CMAKE_GENERATOR STREQUAL "Ninja Multi-Config")
list(APPEND ov_options CMAKE_DEFAULT_BUILD_TYPE)
endif()
else()

View File

@ -33,6 +33,7 @@ function(build_docs)
set(DOXYGEN_MAPPING_SCRIPT "${SCRIPTS_DIR}/create_mapping.py")
set(DOCS_MAPPING_SCRIPT "${SCRIPTS_DIR}/create_doc_mapping.py")
set(BREATHE_APIDOC_SCRIPT "${SCRIPTS_DIR}/apidoc.py")
set(OV_INSTALLATION_SCRIPT "${SCRIPTS_DIR}/install_appropriate_openvino_version.py")
# Doxygen/Sphinx setup
set(DOXYGEN_XML_OUTPUT "${DOCS_BUILD_DIR}/xml")
@ -62,7 +63,9 @@ function(build_docs)
if(${ENABLE_PYTHON_API})
list(APPEND commands COMMAND ${CMAKE_COMMAND} -E cmake_echo_color --green "STARTED preprocessing OpenVINO Python API")
list(APPEND commands COMMAND ${Python3_EXECUTABLE} -m pip install openvino)
list(APPEND commands COMMAND ${Python3_EXECUTABLE} ${OV_INSTALLATION_SCRIPT}
--ov_dir=${SPHINX_SETUP_DIR}
--python=${Python3_EXECUTABLE})
list(APPEND commands COMMAND ${CMAKE_COMMAND} -E cmake_echo_color --green "FINISHED preprocessing OpenVINO Python API")
endif()

View File

@ -6,7 +6,7 @@ Additional Resources
.. meta::
:description: Learn more about OpenVINO from benchmark results, case studies
:description: Learn more about OpenVINO from benchmark results, case studies
and lists of supported models, operations and devices.
.. toctree::
@ -14,7 +14,7 @@ Additional Resources
:hidden:
additional-resources/glossary
additional-resources/legal-information
Legal and Responsible AI Information <./additional-resources/legal-information>
additional-resources/telemetry
Case Studies <https://www.intel.com/openvino-success-stories>
@ -23,9 +23,9 @@ Additional Resources
:doc:`Glossary <additional-resources/glossary>` contains terms used in OpenVINO.
:doc:`Legal Information <additional-resources/legal-information>` has trademark information and other legal statements.
:doc:`Legal and Responsible AI Information <additional-resources/legal-information>` provides trademark information and other legal statements.
:doc:`OpenVINO™ Telemetry <additional-resources/telemetry>` has detailed information on the telemetry data collection.
:doc:`OpenVINO™ Telemetry <additional-resources/telemetry>` has detailed information on the telemetry data collection.
`Case Studies <https://www.intel.com/openvino-success-stories>`__ are articles about real-world examples of OpenVINO™ usage.

View File

@ -1,7 +1,7 @@
.. {#openvino_docs_Legal_Information}
Legal Information
=================
Legal and Responsible AI Information
=====================================
.. meta::
@ -46,4 +46,12 @@ Intel Global Human Right Principles
Intel is committed to respecting human rights and avoiding causing or contributing to adverse
impacts on human rights. See `Intel's Global Human Rights Principles <https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf>`__.
Intel's products and software are intended only to be used in applications that do not cause or
contribute to adverse impacts on human rights.
contribute to adverse impacts on human rights.
Model Card Statement
###########################################################
We recommend that users, wherever you are sourcing the model from, should check for a model card,
consult the model card for each model you access and use, and create one if you are developing
or updating a model. A model card is a short document that provides key information to assess
performance and validation and ensure appropriate use.

View File

@ -1,5 +1,3 @@
.. {#openvino_docs_performance_benchmarks}
Performance Benchmarks
======================
@ -12,6 +10,7 @@ Performance Benchmarks
:maxdepth: 1
:hidden:
performance-benchmarks/generativeAI-benchmarks
performance-benchmarks/performance-benchmarks-faq
OpenVINO Accuracy <performance-benchmarks/model-accuracy-int8-fp32>
performance-benchmarks/getting-performance-numbers
@ -23,6 +22,8 @@ and :doc:`OpenVINO Model Server <../ovms_what_is_openvino_model_server>`, for a
selection of public neural networks and Intel® devices. The results may help you decide which
hardware to use in your applications or plan AI workload for the hardware you have already
implemented in your solutions. Click the buttons below to see the chosen benchmark data.
For more detailed view of performance numbers for generative AI models, check the
:doc:`Generative AI Benchmark Results <./performance-benchmarks/generativeAI-benchmarks>`
.. grid:: 1 1 2 2
:gutter: 4
@ -163,7 +164,7 @@ connection is dedicated only to measuring performance.
The benchmark setup for OVMS consists of four main parts:
.. image:: ../_static/images/performance_benchmarks_ovms_02.png
.. image:: ../assets/images/performance_benchmarks_ovms_02.png
:alt: OVMS Benchmark Setup Diagram
* **OpenVINO™ Model Server** is launched as a docker container on the server platform and it

View File

@ -0,0 +1,8 @@
Generative AI Benchmark Results
===================================
This page will give you a detailed information on how OpenVINO performs running a selection of
Generative AI models.

View File

@ -1,5 +1,3 @@
.. {#system_requirements}
System Requirements
===================
@ -30,6 +28,7 @@ CPU
.. tab-item:: Supported Operating Systems
* Ubuntu 24.04 long-term support (LTS), 64-bit (Kernel 6.8+)
* Ubuntu 22.04 long-term support (LTS), 64-bit (Kernel 5.15+)
* Ubuntu 20.04 long-term support (LTS), 64-bit (Kernel 5.15+)
* Ubuntu 18.04 long-term support (LTS) with limitations, 64-bit (Kernel 5.4+)
@ -59,6 +58,7 @@ GPU
.. tab-item:: Supported Operating Systems
* Ubuntu 24.04 long-term support (LTS), 64-bit
* Ubuntu 22.04 long-term support (LTS), 64-bit
* Ubuntu 20.04 long-term support (LTS), 64-bit
* Windows 10, 64-bit
@ -75,7 +75,7 @@ GPU
for information about your processor.
* While this release of OpenVINO supports Ubuntu 20.04, the driver stack
for Intel discrete graphic cards does not fully support Ubuntu 20.04.
We recommend using Ubuntu 22.04 when executing on discrete graphics.
We recommend using Ubuntu 22.04 and later when executing on discrete graphics.
* The following minimum (i.e., used for old hardware) OpenCL™ driver's versions
were used during OpenVINO internal validation: 22.43 for Ubuntu 22.04, 21.48
for Ubuntu 20.04 and 21.49 for Red Hat Enterprise Linux 8 (some hardware may require
@ -88,6 +88,7 @@ Intel® Neural Processing Unit
.. tab-item:: Operating Systems for NPU
* Ubuntu 24.04 long-term support (LTS), 64-bit
* Ubuntu 22.04 long-term support (LTS), 64-bit
* Windows 11, 64-bit (22H2, 23H2)
@ -106,6 +107,7 @@ Operating systems and developer environment
.. tab-item:: Linux OS
* Ubuntu 24.04 with Linux kernel 6.8+
* Ubuntu 22.04 with Linux kernel 5.15+
* Ubuntu 20.04 with Linux kernel 5.15+
* Red Hat Enterprise Linux 8 with Linux kernel 5.4

Some files were not shown because too many files have changed in this diff Show More