[NPUW]Annotate each Add in SDPA to make per-ATTN-subgraph mask-skipping decisions - #37407
Open
intelgaoxiong wants to merge 1 commit into
Open
[NPUW]Annotate each Add in SDPA to make per-ATTN-subgraph mask-skipping decisions#37407intelgaoxiong wants to merge 1 commit into
intelgaoxiong wants to merge 1 commit into
Conversation
github-actions
Bot
added
category: NPU
intelgaoxiong
marked this pull request as ready for review
August 13, 2026 02:07
intelgaoxiong
changed the title
intelgaoxiong
requested review from
AlexanderKalistratov,
GuoliangShiIntel,
dmatveev and
kkoryun
August 13, 2026 07:43
intelgaoxiong
force-pushed
the
xiong/per_layer_annotate
branch
from
August 13, 2026 08:33
6e5efcf to
5933eaf
Compare
Contributor
Author
|
@dmatveev @kkoryun @AlexanderKalistratov Could you please review the PR? Thanks! |
…isions. Add interface to get per-SDPA's mask type. Add unit test. Signed-off-by: intelgaoxiong <xiong.gao@intel.com>
intelgaoxiong
marked this pull request as draft
August 14, 2026 11:13
intelgaoxiong
marked this pull request as ready for review
August 14, 2026 11:52
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Details:
The PR introduced a new pass for per-layer annotation and mask type analysis.
The per-layer mask type information will be used by model with hybrid attention for:
Tickets:
AI Assistance: