-
Notifications
You must be signed in to change notification settings - Fork 617
Retuned CK GMM fp8/bf16 with perf fixes #3851
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
This pull request was exported from Phabricator. Differential Revision: D71140320 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
This pull request was exported from Phabricator. Differential Revision: D71140320 |
99debef
to
13b92cf
Compare
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
13b92cf
to
80d61d3
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
80d61d3
to
57bf707
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
57bf707
to
41ecfc1
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
41ecfc1
to
9e21be6
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
9e21be6
to
a4ce24b
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
a4ce24b
to
3325fd4
Compare
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
This pull request was exported from Phabricator. Differential Revision: D71140320 |
3325fd4
to
5edd274
Compare
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
63d09fe
to
295c720
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
295c720
to
cbcf556
Compare
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
This pull request was exported from Phabricator. Differential Revision: D71140320 |
cbcf556
to
9547aa4
Compare
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
9547aa4
to
ce8b9c7
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
ce8b9c7
to
045c27a
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
045c27a
to
bd97424
Compare
This pull request was exported from Phabricator. Differential Revision: D71140320 |
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
bd97424
to
27e058c
Compare
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320
This pull request was exported from Phabricator. Differential Revision: D71140320 |
27e058c
to
94cd6da
Compare
Summary: Pull Request resolved: pytorch#3851 X-link: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Differential Revision: D71140320 Reviewed By: mxz297
This pull request has been merged in 5a1b835. |
Summary: X-link: pytorch#3851 Pull Request resolved: facebookresearch/FBGEMM#941 - Fixed launch bound for grouped gemm - Retuned fp8 gmm - Retuned fp8/bf16 GMM for 17Bx16/128 with auto-gen instances (D71528034) Reviewed By: mxz297 Differential Revision: D71140320 fbshipit-source-id: 3da0ec9935bb5edfe854a3084d3660f7d2abb4ec
Summary:
Differential Revision: D71140320