fix: remove custom scaled bmm op on cpu and fix fp8 test #187
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
Signed-off-by: Andrea Fasoli <[email protected]>
andrea-fasoli
requested review from
BrandonGroth,
chichun-charlie-liu,
kcirred,
nwang-ibm and
tharapalanivel
as code owners
Collaborator
Author
|
needs fix for backward compatibility with torch <= 2.7 |
Signed-off-by: Andrea Fasoli <[email protected]>
Signed-off-by: Andrea Fasoli <[email protected]>
chichun-charlie-liu
approved these changes
Oct 17, 2025
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Outdated suggestions cannot be applied.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.
Description of the change
Removing CPU version of custom OP
scaled_mm_outwhich has been introduced in the ATen set from torch 2.8.We will be using torch native scaled_mm_out version when running on CPU from now on.
Also, fixing bug in FP8 unit test giving rise to size mismatch error (note: this test is typically not run as part of CI/CD because it requires torchao and fms installation, as well as GPU with compute >= 8.0).
Related issues or PRs
Relates to torch 2.8 enablement for FMS-MO discussed at: #177