[NPU] flex_attention: enable preload + lazy-load for large tensors - #438
Open
OuYangxin12 wants to merge 1 commit into
Open
[NPU] flex_attention: enable preload + lazy-load for large tensors#438OuYangxin12 wants to merge 1 commit into
OuYangxin12 wants to merge 1 commit into
Conversation
Contributor
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
Add enable_preload=True and enable_dynamic_cv_pipeline=False to the three kernel launch sites (fwd, bwd-dq, bwd-dkdv).
OuYangxin12
force-pushed
the
hw/950-perf-flex-attn-preload-lazyload
branch
from
August 3, 2026 09:07
05043e8 to
8f8df1d
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add enable_preload=True and enable_dynamic_cv_pipeline=False to the three kernel launch sites (fwd, bwd-dq, bwd-dkdv). Insert cv_pipeline_lazy_load compile_hint on large 2D data tensors (q, k, v, do) only — scalar index loads and small 1D tensors are excluded since their buffer expansion is negligible and extra DMA would be a net regression.