Support tuning cache for Cutlass FP8 GEMM #4301
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: D75541025 |
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 12, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 12, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 12, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 12, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 12, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 12, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
added 3 commits
June 13, 2025 14:09
Differential Revision: D75540999
Differential Revision: D75541013
Differential Revision: D75806957
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
cthi
added a commit
to cthi/FBGEMM-1
that referenced
this pull request
Jun 13, 2025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
Summary: Pull Request resolved: pytorch#4301 X-link: facebookresearch/FBGEMM#1377 This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics. - I refactored the kernel dispatch logic to instead return the kernel function, as it removes some duplication of the kernel invoke. - The next diff in this stack will add the new kernels D75820688, to make the review easier - Note that we are having some issues with adding the new kernels, as I have found this kernel is actually compiling 12 variants for each configuration, see D75820688 for more context. So for now we won't add the new kernels in D75820688, but we can just onboard it to auto tuning incase someone wants to compile them locally. Will revisit D75820688 later. Reviewed By: q10, jiawenliu64 Differential Revision: D75541025
|
This pull request was exported from Phabricator. Differential Revision: D75541025 |
|
This pull request has been merged in 4c9313f. |
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:
This diff adds support for the tuning cache to the kernel. There should be no performance changes to the existing heuristics.
Reviewed By: q10, jiawenliu64
Differential Revision: D75541025