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

fixup: src: introduce quant_entry_t and refactor arg_scales_t to rely on it #2657

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

dzarukin
Copy link
Contributor

This fixes #2572.
Patches aarch64 brgemm dispatching without scales involved.

@Ryo-not-rio, you probably may use this commit for your performance regression tracking. It's a dispatching issue, performance should increase significantly (or should have caught a major regression).

@dzarukin dzarukin requested a review from a team as a code owner February 11, 2025 01:29
@github-actions github-actions bot added the platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 label Feb 11, 2025
@vpirogov
Copy link
Member

@dzarukin, pls revert #2599 as part of this PR.

@dzarukin dzarukin force-pushed the dzarukin/fix_aarch64_brgemm branch from 58fa6ad to 7264c57 Compare February 11, 2025 17:57
@dzarukin dzarukin requested a review from a team as a code owner February 11, 2025 17:57
@dzarukin
Copy link
Contributor Author

@dzarukin, pls revert #2599 as part of this PR.

Thanks for pointing this out. Reverted.

@github-actions github-actions bot added the devops Github automation label Feb 11, 2025
@vpirogov
Copy link
Member

ping @oneapi-src/onednn-cpu-aarch64

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
devops Github automation platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
Projects
None yet
Development

Successfully merging this pull request may close these issues.

test_graph_unit_dnnl_convolution_cpu fails on AArch64 CI after recent quantization refactor
2 participants