score-mod backward SM100 cleanup #2130
Closed
+233
−17
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
drisspg
added a commit
that referenced
this pull request
Jan 3, 2026
stack-info: PR: #2130, branch: drisspg/stack/4
drisspg
force-pushed
the
drisspg/stack/3
branch
from
7b2337d to
b84e7f3
Compare
drisspg
force-pushed
the
drisspg/stack/4
branch
from
c76faa1 to
77c5111
Compare
This was referenced Jan 3, 2026
drisspg
added a commit
to drisspg/flash-attention
that referenced
this pull request
Jan 3, 2026
stack-info: PR: Dao-AILab#2130, branch: drisspg/stack/4
drisspg
force-pushed
the
drisspg/stack/4
branch
from
77c5111 to
c01f4de
Compare
drisspg
added a commit
to drisspg/flash-attention
that referenced
this pull request
Jan 5, 2026
stack-info: PR: Dao-AILab#2130, branch: drisspg/stack/4
drisspg
force-pushed
the
drisspg/stack/4
branch
from
c01f4de to
0b7748b
Compare
drisspg
added a commit
to drisspg/flash-attention
that referenced
this pull request
Jan 5, 2026
stack-info: PR: Dao-AILab#2130, branch: drisspg/stack/4
drisspg
force-pushed
the
drisspg/stack/4
branch
from
0b7748b to
ca9049d
Compare
Adds score_mod and mask_mod support to SM90 backward pass: - score_mod, score_mod_bwd, mask_mod, has_aux_tensors parameters - apply_score_mod() and apply_score_mod_bwd() methods - fastdiv_mods and aux_tensors plumbing through kernel/mma - mask_mod application in mask_fn for both block-sparse and dense paths - Score modification in mma_one_m_block before softmax stack-info: PR: #2137, branch: drisspg/stack/8
stack-info: PR: #2130, branch: drisspg/stack/4
drisspg
force-pushed
the
drisspg/stack/4
branch
from
ca9049d to
62cc64e
Compare
drisspg
commented
Jan 5, 2026
| grad_tensor, | ||
| score_tensor, | ||
| index_tensor, | ||
| thr_copy_t2r, |
Collaborator
Author
There was a problem hiding this comment.
let me double check this top commit
drisspg
force-pushed
the
drisspg/stack/8
branch
from
94a0c5c to
759373c
Compare
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.
Stacked PRs:
score-mod backward SM100 cleanup
These failures are existing and appear fringe of tolerance