[Feat] Sage Attention Kernels Support for sm80, sm89, sm90 #9848
Conversation
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
|
Thanks for your contribution! |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #9848 +/- ##
===========================================
- Coverage 50.48% 50.35% -0.13%
===========================================
Files 755 756 +1
Lines 121257 121559 +302
===========================================
- Hits 61215 61214 -1
- Misses 60042 60345 +303 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
l1cacheDell
changed the title
chang-wenbin
approved these changes
Mar 4, 2025
yuanlehome
reviewed
Mar 5, 2025
paddlenlp/experimental/transformers/fused_transformer_layers.py
Outdated
Show resolved
Hide resolved
yuanlehome
reviewed
Mar 5, 2025
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Outdated suggestions cannot be applied.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.
PR types
New features | Others: add new kernels for LLM prefilling accelerating.
PR changes
See file changes in
csrc/gpu/sage_attn_kernels/*Description
This PR added sage attention support kernels implemented for Paddle and PaddleNLP.
Sage Attention for 8-bit acceleration on attention inference, similar work to FA2 & FA3 but speed up 1.1 - 2.1 x compared to Flash Attention, with even lower gpu memory allocation. See SageAttention Official Repository and their paper (accepted by ICLR 2025) for more info.
This PR is currently working in progress.
Reviewing this PR may takes a lot...