Andrii Staikov
Andrii Staikov
> @CuriousPanCake, Please provide the status for the same set of models that was mentioned in #24336. Yep, I've run the tests for all the models available in the testing...
> I'll attach the logs in a second. [page_attention_test_full.txt](https://github.com/openvinotoolkit/openvino/files/15247222/page_attention_test_full.txt)
Added Tile. Tests to be added/fixed later.
> Could you also in this PR fix here > > https://github.com/openvinotoolkit/openvino/blob/62a1f1b50c93268f96c325760442765115d01d74/.github/workflows/job_pytorch_models_tests.yml#L138 > > Currently these models run twice in validation, in `PyTorch Models Tests Not Timm or Torchvision` and...
> > Could you also in this PR fix here > > https://github.com/openvinotoolkit/openvino/blob/62a1f1b50c93268f96c325760442765115d01d74/.github/workflows/job_pytorch_models_tests.yml#L138 > > > > Currently these models run twice in validation, in `PyTorch Models Tests Not Timm...
> may we have tests and comments with explanation (why it is equivalent to paged attention)? This PR is a part of supporting PagedAttention transformation for LLMs. Right now, I...
We're currently working on this issue. It requires some investigations and changes in Convolution transformations.
The issue has been fixed https://github.com/openvinotoolkit/openvino/pull/25876 @ListonQH , please verify
Hello! Can we expect this to be merged in the nearest future?
First, we need to merge the runtime changes: https://github.com/openvinotoolkit/openvino/pull/32570