Enable CUTLASS grouped GEMM for pretraining wgrad on GB200 and H100 #4886
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
@jiawenliu64 has exported this pull request. If you are a Meta employee, you can view the originating diff in D82325651. |
|
@jiawenliu64 has exported this pull request. If you are a Meta employee, you can view the originating diff in D82325651. |
jiawenliu64
force-pushed
the
export-D82325651
branch
from
0fe2c3a to
7d30e87
Compare
jiawenliu64
added a commit
to jiawenliu64/FBGEMM
that referenced
this pull request
Sep 17, 2025
…ytorch#4886) Summary: Pull Request resolved: pytorch#4886 X-link: facebookresearch/FBGEMM#1910 - Enable CUTLASS grouped GEMM for llama4x pretraining wgrad on GB200 and H100 - Optimize performance of pretraining moe shapes on H100 - Support total_K in quantize_bench for wgrad Differential Revision: D82325651
|
@jiawenliu64 has exported this pull request. If you are a Meta employee, you can view the originating diff in D82325651. |
jiawenliu64
added a commit
to jiawenliu64/FBGEMM
that referenced
this pull request
Sep 17, 2025
…ytorch#4886) Summary: Pull Request resolved: pytorch#4886 X-link: facebookresearch/FBGEMM#1910 - Enable CUTLASS grouped GEMM for llama4x pretraining wgrad on GB200 and H100 - Optimize performance of pretraining moe shapes on H100 - Support total_K in quantize_bench for wgrad Differential Revision: D82325651
jiawenliu64
force-pushed
the
export-D82325651
branch
from
7d30e87 to
cc5b529
Compare
…ytorch#4886) Summary: Pull Request resolved: pytorch#4886 X-link: facebookresearch/FBGEMM#1910 - Enable CUTLASS grouped GEMM for llama4x pretraining wgrad on GB200 and H100 - Optimize performance of pretraining moe shapes on H100 - Support total_K in quantize_bench for wgrad Reviewed By: q10 Differential Revision: D82325651
|
@jiawenliu64 has exported this pull request. If you are a Meta employee, you can view the originating diff in D82325651. |
jiawenliu64
force-pushed
the
export-D82325651
branch
from
cc5b529 to
b5c9a1a
Compare
|
This pull request has been merged in 57c2293. |
|
This pull request has been reverted by 53f9e51. |
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.
Summary:
X-link: https://github.com/facebookresearch/FBGEMM/pull/1910
Differential Revision: D82325651