Revert "Optimize fp8 linalg_ext.attention by rework Q@K scaling"
#18112
Conversation
This file contains 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
raikonenfnu
requested review from
Groverkss and
rsuderman
and removed request for
MaheshRavishankar and
hanhanW
|
I don't think this should be a revert... This is a problem with our codegen, not the decomposition or the attention operation. Why is the vector.contract a problem btw? |
Groverkss
approved these changes
Aug 6, 2024
raikonenfnu
force-pushed
the
revert-18031-optimize_fp8_attention
branch
from
06b277d to
8b1d241
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Outdated suggestions cannot be applied.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.
Reverts #18031
Mathematically correct, however since scaling (which is an elementwise mul linalg.generic) happens now before reduction-addf, it unexpectedly becomes a vector.contract after GenericVectorization pass.