[Aiter] upgrade aiter to be compatible with latest TE#209
Closed
GeneDer wants to merge 3 commits into
Closed
Conversation
Signed-off-by: Gene Der Su <e870252314@gmail.com>
Signed-off-by: Gene Der Su <e870252314@gmail.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates the aiter dependency to be compatible with the latest TransformerEngine by upgrading to a newer commit that includes API changes to the _flash_attn_forward function.
Changes:
- Updated aiter package reference to use
amd-aiterand a newer commit hash - Added new parameters (
sink_size,q_descale,k_descale,v_descale) to the_flash_attn_forwardcall to align with the updated API
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| setup.py | Updates aiter dependency to use new package name and commit hash |
| primus_turbo/pytorch/kernels/attention/attention_csrc_impl.py | Adds new parameters to the forward function signature and passes them to _flash_attn_forward |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Member
Author
|
@wenxie-amd @xiaobochen-amd can you help to merge this? We need it to be able to use the latest TE 🙏 |
Signed-off-by: Gene Der Su <e870252314@gmail.com>
Collaborator
Member
Author
|
duplicated with #208 |
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
TE recently updated the aiter commit they are using ROCm/TransformerEngine#354 (aiter @ ed4bdea). There is an api change around calling
_flash_attn_forward. This PR tries to use the new api offered in aiter.