fix gqa cpu nan bug #20521
Merged
fix gqa cpu nan bug #20521
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
tianleiwu
reviewed
May 2, 2024
onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu
Outdated
Show resolved
Hide resolved
|
Could you please enable to run the unit test in CI? |
tianleiwu
reviewed
May 2, 2024
tianleiwu
reviewed
May 2, 2024
tianleiwu
previously approved these changes
May 7, 2024
The test is skipped in CI: |
tianleiwu
reviewed
May 7, 2024
tianleiwu
approved these changes
May 7, 2024
yufenglee
reviewed
May 7, 2024
yufenglee
approved these changes
May 7, 2024
snnn
approved these changes
May 7, 2024
yihonglyu
pushed a commit
that referenced
this pull request
May 9, 2024
### Description There was a bug with gqa on cpu where on token case, with batch_size > 1, and with past_present_share_buffer off, the output would occasionally contain nans. this pr fixes that. it also updates documentation and fixes posid gen for rotary in cuda in prompt case. ### Motivation and Context this pr solves the GQA CPU bug as well as updates the documentation and makes seqlens_k irrelevant for prompt case, which is useful to prevent user error.
poweiw
pushed a commit
to poweiw/onnxruntime
that referenced
this pull request
Jun 25, 2024
### Description There was a bug with gqa on cpu where on token case, with batch_size > 1, and with past_present_share_buffer off, the output would occasionally contain nans. this pr fixes that. it also updates documentation and fixes posid gen for rotary in cuda in prompt case. ### Motivation and Context this pr solves the GQA CPU bug as well as updates the documentation and makes seqlens_k irrelevant for prompt case, which is useful to prevent user error.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
There was a bug with gqa on cpu where on token case, with batch_size > 1, and with past_present_share_buffer off, the output would occasionally contain nans. this pr fixes that. it also updates documentation and fixes posid gen for rotary in cuda in prompt case.
Motivation and Context
this pr solves the GQA CPU bug as well as updates the documentation and makes seqlens_k irrelevant for prompt case, which is useful to prevent user error.