HETERO plugin ('HETERO:GPU,CPU') raises an error [GPU] Mismatch tensor
and port types: i64 vs i32
### Details:
- *Do not convert Result element type after Extension if required;*
- *Eliminate converts after the second call of the ConvertPrecisoin
pass;*
- *Support string input in the `benchmark_app`*.
### Tickets:
- *136752*
### Details:
- This PR introduces a PR labeller for external PRs. It will add the
`ExternalPR` label to a PR whose author is not in the `openvino`
collaborator list.
It will not work from a PR as it has a `pull_request_target` trigger for
the secrets. I've tested it locally.
### Tickets:
- *135090*
### Details:
- Limit NF4 conversion to FP16 -> NF4 in convert operator as values are
correctly quantized, Not support NF4 conversion to/from other types.
### Tickets:
- [CVS-135304](https://jira.devtools.intel.com/browse/CVS-135304)
This fixes#23566
Implemented Model.setFriendlyName and Model.getFriendlyName in Node.js
api
- Added Parameter Validation
- Added Tests in model.test.js
---------
Co-authored-by: Vishniakov Nikolai <nikolai.vishniakov@intel.com>
This Fixes#23441 issue.
Details:
1. Modified get_shape() method to report error in case any argument is
passed.
2. Added Required Tests for the above in `tensor.test.js`.
---------
Co-authored-by: Vishniakov Nikolai <nikolai.vishniakov@intel.com>
Co-authored-by: Alicja Miloszewska <alicja.miloszewska@intel.com>
### Details:
- The compilation of a model without inputs was failing because the
serialization in zero compiler expected at least one input.
### Tickets:
- EISW-107905
### Details:
- In the case of shape-agnostic gemm kernel, `TILE_K_NOT_DIVISIBLE` and
`TILE_N_NOT_DIVISIBLE` can be expressed as a conditional branches rather
than constant values, in which case performance could be degraded.
- This PR changes a gemm impl to have four OpenCL kernels with
`TILE_K_NOT_DIVISIBLE` and `TILE_N_NOT_DIVISIBLE` of 0 and 1. Just
before enqueuing a gemm kernel, it checks the value of
`TILE_K_NOT_DIVISIBLE` and `TILE_N_NOT_DIVISIBLE` on the host side, and
chooses one of them.
### Tickets:
- 134699
### Details:
- Follow up some comments from
https://github.com/openvinotoolkit/openvino/pull/23513
- Fuse `unsqueeze` layer into `gemm` layer for indirect gemm
- before : [`kv_cache`] --> [`unsqueeze`] --> `gemm`
- after : [`kv_cache`] --> `gemm`
- Simplify fusion pass and logic as `unsqueeze` is fused together
### Tickets:
- 136567
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
### Details:
- If a process lacks CAP_SYS_NICE capability, mbind fails with an error
"Operation not permitted". We should either ignore the result (just log)
or throw an exception. Also, as an option, we could check if
CAP_SYS_NICE is set before performing any mbind related logic.
- For now just log to the debug
### Details:
This PR introduces a GHA pipeline rerunner. It should scan the failed
workflows' logs and re-run those having known sporadic errors.
The rerunner is a Python script which is used by a dedicated workflow.
The workflow will not run from this PR, it needs to be in `master`. I've
checked the workflow and script in the private repo.
### Tickets:
- *136935*
* Created new article about Release Policy,
* Moved System Requirements Article under Release Notes.
* Removed environment variables info from torch.compile article.
Jira: 132590
---------
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
### Details:
- The example use case is to generalize processing of the operation
with and without bias.
When the operation has no bias, it is possible to create memory
using empty memory descriptor, and use the exact same code as if bias
actually exists.
- Many headers are affected to break the chain of implicit intersecting
includes
### Tickets:
- 131590
### Todo:
- [ ] Add unit tests
### Details:
Updated ReadValue, Loop ref implementations
Added a new functionality to template plugin to collect Variables inside
Multisubgraph ops
Added a new functional test
### Tickets:
- *CVS-135198*
### Details:
- Fix build of extensions tests for frontends when build of fronded is
disabled.
- Remove the warnings as error for unused functions.
### Tickets:
- N/A
### Details:
- Add LP specializations for cast, fill, write data.
- Remove not used private members.
- Move public non-template members to cpp.
- Optimize bin-size (Ubuntu 20, Release, gcc11):
- No LTO around 421 KiB
- LTO around 10.6 KiB
- Add common elements byte size util function.
- Prepare to use new type like u2, u3, u6
### Tickets:
- Part of
[CVS-119224](https://jira.devtools.intel.com/browse/CVS-119224)
### Details:
- Automatically adding the node name to all autogenerated constants.
Example: `NodeName/Constant_X`
- Removed `apply_affix_on` approach.
- Adjusted testcases to check compatibility.
- The change is backward incompatible -- breaking cases unknown.
- To be added: extend other operations `as_node/as_nodes` to follow this
example, as this approach is not automatically applicable.
### Tickets:
- CVS-133139
---------
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
### Details:
- Initialization of OV Opset15
(Discussed internally and agreed to introduce new opset in 2024.2)
To provide more agile approach, this PR has been updated with an idea
(proposed by @mmikolajcz) to include only new operators within the new
Opset, and fill it up at the end of the development period (not
necessarily per release).
This should lead to infrequent introduction of further opsets.
\* Currently common opsets tests rely on Parameter/ShapeOf/Convert in
every opset, so they were added.
But this approach for opset testing should be revised.
### Tickets:
- 138268, 131683
This Fixes#23430 .
Details:
1. Added get_versions() method definition into bindings (core_wrap.hpp)
2. Implemented this method in bindings (core_wrap.cpp)
3. Add interface implementation to addon.ts
4. Added basic js test for this method in
`src/bindings/js/node/tests/basic.test.js`
CC: @vishniakov-nikolai
---------
Co-authored-by: Vishniakov Nikolai <nikolai.vishniakov@intel.com>
Bartlomiej Bielawa