natas_hw
/
openvino
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
15,670 Commits 48 Branches 60 Tags 1.3 GiB
Commit Graph

18 Commits

Author SHA1 Message Date
Maxim Vafin b8ced3dfc7
Change opt-125m-gptq model (#24899) 
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
 2024-06-07 14:50:30 +04:00
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
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
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
Maxim Vafin 03fa47a2ff
Refactor hf GHA tests (#24048) 
### Details:
 - *Refactor hf tests*

### Tickets:
 - *ticket-id*
 2024-04-16 14:27:34 +00:00
Maxim Vafin 2eb09a4d07
[FX] Remove unused code from FX decoder (#23954) 
### Details:
 - *Remove unused code from FX decoder*

### Tickets:
 - *ticket-id*
 2024-04-11 12:42:52 +00:00
Maxim Vafin 4ef40f0f0e
[PT FE] Fix GHA model tests (#23846) 
### Details:
 - *Added `kornia` dependency for lightglue model*
 - *Disable GFPGAN since it doesn't support latest `torchvision`*
 - *Remove `transfo-xl-wt103` as not supported on latest `transformers`*
 - *Remove XFAIL from `facebook/levit-128S`*

### Tickets:
 - *ticket-id*
 2024-04-05 06:30:50 +00:00
Maxim Vafin ee2962a50c
[OVC] Allow models obtained from torch.export (#23815) 
### Details:
 - *Allow models obtained from `torch.export`*

### Tickets:
 - *ticket-id*
 2024-04-03 05:56:46 +00:00
Maxim Vafin fba93854cb
[PT FE] Fix issue with aten.copy in FX graph (#23711) 
### Details:
 - *Fix translation for `aten.copy.default`*
 - *Add support for `aten.rand.default`*
 - *Support `vit-mae` model*
 - *Update hf model list with newly added models since list creation*

### Tickets:
 - *CVS-133732*
 2024-03-28 13:01:06 +00:00
Maxim Vafin 99715bf875
[PT FE] Add more operators for FX graph (#23698) 
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
 2024-03-27 07:46:53 +00:00
Maxim Vafin b10877f6e8
[PT FE] Resolve i64 usage in frontend (#23518) 
### Details:
 - *Support lightglue*
 - *Support int64 as scalar in PyTorch Frontend*

### Tickets:
 - *CVS-127326, CVS-134328*
 2024-03-26 15:57:00 +00:00
Jacek Pawlak 239466ca5d
copyright year update (#23370) 
New PR due to merge
conflicts(https://github.com/openvinotoolkit/openvino/pull/22917)

Updated the copyright year from 2018-2023 to 2018-2024 in all openvino
files

Ref. to script: CVS-101144

Command used:
```bash
git grep -lz '2018-2023 Intel Corporation' | xargs -0 sed -i '' -e 's/2018-2023 Intel Corporation/2018-2024 Intel Corporation/g'
```
 2024-03-14 09:37:02 +00:00
Maxim Vafin ad8d6ef35d
[PT FE] Support aten.reflection_pad{1,2,3}d.default (#23379) 
### Details:
- *Support `aten.reflection_pad1d.default`,
`aten.reflection_pad2d.default` and `aten.reflection_pad3d.default`*

### Tickets:
 - *ticket-id*
 2024-03-13 22:39:37 +00:00
Maxim Vafin 4f5c2a7a93
Change model since previous persimmon model was removed (#23201) 
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
 2024-03-05 10:29:11 +00:00
Maxim Vafin 4edb040869
Fix timm filter and run timm models in parallel (#23116) 
### Details:
 - *Update list of timm models to comply with new version of timm*
- *Run timm models and torchvision models in trace and export model in
parallel*

### Tickets:
 - *ticket-id*
 2024-03-01 10:59:32 +00:00
Maxim Vafin 8b792927fa
[PT FE] Support multiple FX operations (#23112) 
### Details:
 - *Unpack nested tuples at model outputs*
 - *Support for `aten.cat.default` with default axis*
 - *Support `aten::reciprocal_` and `aten::abs_` for TorchScript case*
 - *Support:*
    *  `aten.adaptive_max_pool3d.default`
    *  `aten.adaptive_max_pool{N}d.default`
    *  `aten.amin.default`
    *  `aten.argmin.default`
    *  `aten.bitwise_{XXX}.default`
    *  `aten.clamp_max.default`
    *  `aten.clamp_{max/min}.Tensor`
    *  `aten.fill.Tensor`
    *  `aten.flip.default`
    *  `aten.fmod.{Scalar/Tensor}`
    *  `aten.ge.{Scalar/Tensor}`
    *  `aten.gt.Tensor`
    *  `aten.index_select.default`
    *  `aten.le.{Scalar/Tensor}`
    *  `aten.log{10/1p/2}.default`
    *  `aten.{max/maximum/mean/min/minimum}.default`
    *  `aten.min.dim`
    *  `aten.ne.Tensor`
    *  `aten.pow.{Scalar/Tensor_Tensor}`
    *  `aten.reciprocal.default`
    *  `aten.rsub.Tensor`
    *  `aten.scatter.value`
    *  `aten.select_scatter.default`
    *  `aten.sign.default`
    *  `aten.sqrt.default`
    *  `aten.sum.default`
    *  `aten.unfold.default`
    *  `aten.var.correction`
    *  *trigonometric ops*

 - *Enabled layer tests for added ops for torch.export case*

### Tickets:
 - *ticket-id*
 2024-02-29 16:14:31 +00:00
Maxim Vafin ed6b3a5333
Disable torch.export for nightly (#23114) 
### Details:
 - *item1*
 - *...*

### Tickets:
 - *ticket-id*
 2024-02-27 21:08:11 +04:00
Anastasiia Pnevskaia a819605986
[TF FE] Test TF Hugging Face models (#22970) 
### Details:
 - TF Hugging face tests

### Tickets:
 - 132904

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2024-02-26 12:41:09 +00:00