Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CPU] Fixed accuracy of compressed matmul with scalar scale #28431

Conversation

dmitry-gorokhov
Copy link
Contributor

@dmitry-gorokhov dmitry-gorokhov commented Jan 14, 2025

Details:

  • This PR fixes accuracy of compressed Matmuls with scalar scale
  • The issue was on micro-kernel level: incorrect offset during scales load

oneDNN PR: openvinotoolkit/oneDNN#270

Tickets:

@dmitry-gorokhov dmitry-gorokhov added this to the 2025.0 milestone Jan 14, 2025
@dmitry-gorokhov dmitry-gorokhov self-assigned this Jan 14, 2025
@dmitry-gorokhov dmitry-gorokhov requested review from a team as code owners January 14, 2025 08:50
@github-actions github-actions bot added category: IE Tests OpenVINO Test: plugins and common category: GPU OpenVINO GPU plugin labels Jan 14, 2025
@@ -74,6 +75,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_MatMulCompressedWeights_corner_cases,
::testing::ValuesIn(decompression_precisions_corner_cases),
::testing::Values(ov::element::undefined),
::testing::ValuesIn(transpose_weights),
::testing::Values(DecompressionType::full),
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe we can add DecompressionType::scalar multiply instances for ARM? If ARM has the same issue as X64, the failed tests will be a good indication: we could skip them for now with the corresponding comment (e.g. with ticket number)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We are using oneDNN ref mamtul to cover compression on ARM now. So the fix doesn't affect ARM behavior.
However the idea the cover some corner cases for ARM sounds reasonable. Will follow-up in separate PR.

Copy link
Contributor

@p-durandin p-durandin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK for GPU change

@dmitry-gorokhov dmitry-gorokhov added this pull request to the merge queue Jan 14, 2025
Merged via the queue into openvinotoolkit:master with commit 96d48e8 Jan 14, 2025
185 checks passed
@dmitry-gorokhov dmitry-gorokhov deleted the fix/compressed_matmul_with_scalar_scale branch January 14, 2025 15:50
MirceaDan99 pushed a commit to MirceaDan99/openvino that referenced this pull request Jan 22, 2025
…toolkit#28431)

### Details:
 - This PR fixes accuracy of compressed Matmuls with scalar scale
- The issue was on micro-kernel level: incorrect offset during scales
load

oneDNN PR: openvinotoolkit/oneDNN#270

### Tickets:
 - [CVS-143420](https://jira.devtools.intel.com/browse/CVS-143420)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: CPU OpenVINO CPU plugin category: GPU OpenVINO GPU plugin category: IE Tests OpenVINO Test: plugins and common Code Freeze
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants