Update heuristic for Cutlass BF16 Grouped GEMM #4138
Closed
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. |
|
This pull request was exported from Phabricator. Differential Revision: D74836650 |
cthi
pushed a commit
to cthi/FBGEMM-1
that referenced
this pull request
May 19, 2025
Summary: X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
cthi
pushed a commit
to cthi/FBGEMM-1
that referenced
this pull request
May 19, 2025
Summary: X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
|
This pull request was exported from Phabricator. Differential Revision: D74836650 |
cthi
pushed a commit
to cthi/FBGEMM-1
that referenced
this pull request
May 19, 2025
Summary: Pull Request resolved: pytorch#4138 X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
|
This pull request was exported from Phabricator. Differential Revision: D74836650 |
cthi
pushed a commit
to cthi/FBGEMM-1
that referenced
this pull request
May 19, 2025
Summary: Pull Request resolved: pytorch#4138 X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
Summary: We plan to make some changes to the heuristics, first refactor a bit to parallelize kernel compilation, such as in FP8 rowwise. Differential Revision: D74760416
cthi
pushed a commit
to cthi/FBGEMM-1
that referenced
this pull request
May 20, 2025
Summary: X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
cthi
pushed a commit
to cthi/FBGEMM-1
that referenced
this pull request
May 20, 2025
Summary: X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
|
This pull request was exported from Phabricator. Differential Revision: D74836650 |
cthi
pushed a commit
to cthi/FBGEMM-1
that referenced
this pull request
May 20, 2025
Summary: Pull Request resolved: pytorch#4138 X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
Summary: Pull Request resolved: pytorch#4138 X-link: facebookresearch/FBGEMM#1220 This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes. Reviewed By: jianyuh Differential Revision: D74836650
|
This pull request was exported from Phabricator. Differential Revision: D74836650 |
|
This pull request has been merged in 841c22c. |
q10
added a commit
to q10/FBGEMM
that referenced
this pull request
May 22, 2025
- Disable GenAI builds against CUDA 11.8 since it is no longr possible to support GenAI builds against CUDA 11.8.0 as of pytorch#4138
q10
added a commit
to q10/FBGEMM
that referenced
this pull request
May 22, 2025
- Disable GenAI builds against CUDA 11.8 since it is no longr possible to support GenAI builds against CUDA 11.8.0 as of pytorch#4138
q10
added a commit
to q10/FBGEMM
that referenced
this pull request
May 22, 2025
- Disable GenAI builds against CUDA 11.8 since it is no longr possible to support GenAI builds against CUDA 11.8.0 as of pytorch#4138
q10
added a commit
to q10/FBGEMM
that referenced
this pull request
May 22, 2025
- Disable GenAI builds against CUDA 11.8 since it is no longr possible to support GenAI builds against CUDA 11.8.0 as of pytorch#4138
facebook-github-bot
pushed a commit
that referenced
this pull request
May 22, 2025
Summary: X-link: facebookresearch/FBGEMM#1255 - Disable GenAI builds against CUDA 11.8 since it is no longr possible to support GenAI builds against CUDA 11.8.0 as of #4138 Pull Request resolved: #4173 Reviewed By: jiawenliu64 Differential Revision: D75229752 Pulled By: q10 fbshipit-source-id: e9626799d371ee2671f9062df1933d3caea65087
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/1220
This diff updates the heuristic used for Cutlass BF16 grouped gemm, improving performance in some important shapes.
Differential Revision: D74836650