Support case when cache_len == 0 #16546
Open
+2
−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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16546
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 4 Unrelated FailuresAs of commit 407a47d with merge base 35eb01a ( NEW FAILURES - The following jobs have failed:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
YIWENX14
added a commit
to YIWENX14/executorch
that referenced
this pull request
Jan 12, 2026
Summary: There's a discrepancy in the SDPA impl when computing w/wo paddings as invalid cache, even it's masked out. For verification purposes, we need to test eager model without paddings to match results with QAT model. The change is to handle cases where `cache_len == 0`, preventing crashes in cache updates. Differential Revision: D90526985
YIWENX14
force-pushed
the
export-D90526985
branch
from
e999cb0 to
dae7892
Compare
Summary: There's a discrepancy in the SDPA impl when computing w/wo paddings as invalid cache, even it's masked out. For verification purposes, we need to test eager model without paddings to match results with QAT model. The change is to handle cases where `cache_len == 0`, preventing crashes in cache updates. Differential Revision: D90526985
YIWENX14
force-pushed
the
export-D90526985
branch
from
dae7892 to
407a47d
Compare
billmguo
approved these changes
Jan 13, 2026
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.
Summary: There's a discrepancy in the SDPA impl when computing w/wo paddings as invalid cache, even it's masked out. For verification purposes, we need to test eager model without paddings to match results with QAT model. The change is to handle cases where
cache_len == 0, preventing crashes in cache updates.Differential Revision: D90526985