fix: pre-download sage_attention kernel before applying backend, remove pinned fa3 kernel version#578
Open
Marius-Graml wants to merge 2 commits intomainfrom
Open
fix: pre-download sage_attention kernel before applying backend, remove pinned fa3 kernel version#578Marius-Graml wants to merge 2 commits intomainfrom
Marius-Graml wants to merge 2 commits intomainfrom
Conversation
The submodule-level set_attention_backend in diffusers does not trigger the kernel download, leaving kernel_fn as None and causing a TypeError. This adds an explicit _maybe_download_kernel_for_backend call.
Marius-Graml
changed the title
Marius-Graml
changed the title
|
This PR has been inactive for 10 days and is now marked as stale. |
johannaSommer
approved these changes
Mar 31, 2026
Member
johannaSommer
left a comment
johannaSommer
left a comment
There was a problem hiding this comment.
LGTM but please wait for Begüm's review regarding the version
| Dict[str, Any] | ||
| The algorithm packages. | ||
| """ | ||
| flash_attention_3 = get_kernel("kernels-community/flash-attn3", version="<0.1.0") |
Member
There was a problem hiding this comment.
I know that this was an important fix at some point, so not sure about removing it. Please wait for @begumcig 's review on this, she tackled this back then
| enable_gqa=enable_gqa, | ||
| ) | ||
| else: | ||
| out, _, *_ = torch.ops.flash_attn_pruna._flash_attn_forward( |
Member
There was a problem hiding this comment.
we might need to keep this flexibile depending on the fa3 version we encounter - can we return and check whether the output is a tuple or a tensor and handle it accordingly?
Member
There was a problem hiding this comment.
nevermind i get what you did now, this is great!
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
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.
Description
Currently, there is a bug in the sageattn algorithm. Diffusers has two set_attention_backend methods, one for the whole model and one for the submodules. The submodule-level set_attention_backend in diffusers does not trigger the kernel download, leaving kernel_fn as None and causing a TypeError. This adds an explicit _maybe_download_kernel_for_backend call.
Further, the pinned version of the fa3 kernel is removed such that fa3 works for torch 2.10 now. Note, that some kernel builds return (out, lse), others return just out, depending on torch and cuda version. Thus, this must be handled in the registered torch-op function.
Related Issue
/
Type of Change
How Has This Been Tested?
Run in notebook
Checklist
Additional Notes
/