Use torch._grouped_mm in eager mode #2721
Open
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
This gives a fair comparison between eager and other modes. The constraints mentioned in the comment seem to have been fixed at least for Blackwell.
wujingyue
requested review from
KaelanDt,
lantiga,
mruberry and
t-vi
as code owners
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR enables the use of torch._grouped_mm in eager mode for benchmarking purposes, providing a fair comparison between eager and other modes. Previously, the function was only used during compilation (via torch.compiler.is_compiling() check). The constraints that prevented eager mode usage have been resolved.
Key changes:
- Replaced
torch.compiler.is_compiling()check with availability check based on_grouped_mmvariable - Added
elseclause to set_grouped_mm = Nonefor torch versions < 2.8.0 - Removed outdated comment about constraints requiring offsets to be multiples of 16
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
crcrpar
approved these changes
Nov 11, 2025
Co-authored-by: Masaki <[email protected]>
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Outdated suggestions cannot be applied.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.
This gives a fair comparison between eager and other modes.
The constraints mentioned in the comment seem to have been fixed by pytorch/pytorch#161407
python thunder/benchmarks/benchmark_inference.pyat head runs fine on both Blackwell and Ampere.