CPU FA: disable mask optimization#1935
Merged
Merged
Conversation
ikawrakow
force-pushed
the
ik/cpu_fa_disable_mask_opt
branch
from
caaecb8 to
98cf5ce
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #1910.
The failure mode is triggered when processing a batch for a thread that is working on activation rows that have very few not-masked KV cache entries due to SWA. In that case stepping over the mask in steps of
k_stepmay miss the few non-masked entries, thus resulting in processing only fully masked KV cache entries, which triggers theS > 0assert.