Fix torchAO shape check on fp8 tensors #3057
Merged
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/ao/3057
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit 9c1110a with merge base b47f1a3 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
|
@RandySheriff has exported this pull request. If you are a Meta employee, you can view the originating diff in D83184235. |
Summary: Previously the shape mismatch on input and weight scales caused semi-tensor fall back to dense version, QPS therefore dropped to 20k from 29k. With this fix, we prevented the fall back to ensure the usage of semi-tensor during inferencing, which boosted QPS to [32k](https://www.internalfb.com/intern/paste/P1962815637/) on 10 linears, of shape(10k+, 1k+). Differential Revision: D83184235
RandySheriff
force-pushed
the
export-D83184235
branch
from
7b390b2 to
9c1110a
Compare
|
@RandySheriff has exported this pull request. If you are a Meta employee, you can view the originating diff in D83184235. |
vkuzo
added a commit
that referenced
this pull request
Sep 25, 2025
Summary: #3057 was landed with failing lint, this PR fixes it. Test Plan: ``` ruff format ``` Reviewers: Subscribers: Tasks: Tags:
vkuzo
added a commit
that referenced
this pull request
Sep 25, 2025
Summary: #3057 was landed with failing lint, this PR fixes it. Test Plan: ``` ruff format ``` Reviewers: Subscribers: Tasks: Tags:
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
Differential Revision: D83184235