flash-attn: Add XPU support for flash-attn-2 #30
+21,468
−0
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
|
@danieldk please help review, thanks! |
|
CUDA flash-attn2 is merged: https://github.com/huggingface/kernels-community/tree/main/flash-attn2 Could you rebase the PR on |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
The main contribution of this PR:
flash_attn.fwdandflash_attn.varlen_fwdon XPU.test_flash_attn.pyto support XPU testing.This PR passed local pip install, nix compilation, and UT testing on the XPU. It also passed pip install and UT testing on the CUDA GPU.
Additional:
The test of
test_flash_attn.py::test_flash_attn_kvcacheon CUDA reports an error:RuntimeError: out must have shape (batch_size, seqlen_q, num_heads, head_size_og). I tested the original kernel flash-attn and got the same error, which is unrelated to this PR.