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.

Sign up for GitHub

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

Jump to bottom

[oneDNN][Bug-fix] Add check for min-max tensors in quantized matmul OpKernel. #59437

Merged
merged 1 commit into from Jan 26, 2023
Merged

[oneDNN][Bug-fix] Add check for min-max tensors in quantized matmul OpKernel. #59437

merged 1 commit into from Jan 26, 2023

Conversation

mdfaijul
Copy link
Contributor

This PR fixes NPE (null-pointer exception error) on tensors relevant to quantized matmul OpKernel. Particularly, when an element is accessed with an index, this PR first checks if such index is valid or not.

@google-ml-butler google-ml-butler bot added the size:M CL Change Size: Medium label Jan 24, 2023
@google-ml-butler google-ml-butler bot added the awaiting review Pull request awaiting review label Jan 24, 2023
@github-actions github-actions bot added the kokoro:force-run Tests on submitted change label Jan 24, 2023
@kokoro-team kokoro-team removed kokoro:force-run Tests on submitted change labels Jan 24, 2023
@mdfaijul
Copy link
Contributor Author

@penpornk This PR has a fix on tf.raw_ops.QuantizedMatMulWithBiasAndDequantize. Please help reviewing this. Thanks!

@gbaned gbaned added this to Assigned Reviewer in PR Queue via automation Jan 25, 2023
@gbaned gbaned added the comp:mkl MKL related issues label Jan 25, 2023
penpornk
penpornk requested changes Jan 25, 2023
View reviewed changes
Copy link
Member

@penpornk penpornk left a comment

Choose a reason for hiding this comment

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

Thank you very much for the quick fix!

tensorflow/core/kernels/mkl/mkl_qmatmul_op.cc Show resolved Hide resolved
PR Queue automation moved this from Assigned Reviewer to Reviewer Requested Changes Jan 25, 2023
PR Queue automation moved this from Reviewer Requested Changes to Approved by Reviewer Jan 25, 2023
@google-ml-butler google-ml-butler bot added kokoro:force-run Tests on submitted change ready to pull PR ready for merge process labels Jan 25, 2023
@kokoro-team kokoro-team removed the kokoro:force-run Tests on submitted change label Jan 25, 2023
@penpornk
Copy link
Member

MacOS CPU Python3 failures seem unrelated to this PR:

clang++: error: no such file or directory: 'tensorflow/compiler/mlir/lite/sparsity/sparsify_model.cc'
clang++: error: no input files

@copybara-service copybara-service bot merged commit 8a47a39 into tensorflow:master Jan 26, 2023
PR Queue automation moved this from Approved by Reviewer to Merged Jan 26, 2023
@penpornk penpornk removed the awaiting review Pull request awaiting review label Jan 28, 2023
@gzmkl gzmkl mentioned this pull request Feb 6, 2023
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@penpornk penpornk penpornk approved these changes

Assignees

@penpornk penpornk

@gbaned gbaned

Labels
comp:mkl MKL related issues ready to pull PR ready for merge process size:M CL Change Size: Medium
Projects
PR Queue
  
Merged
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
4 participants
@mdfaijul @penpornk @kokoro-team @gbaned