Skip to content

Update Cutlass to V3.8-2 #3767

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

Closed
wants to merge 2 commits into from
Closed

Conversation

jwfromm
Copy link
Contributor

@jwfromm jwfromm commented Mar 5, 2025

Summary: Update the Codesign copy of cutlass to version 3.8 V2. This includes new features and changes for mixed dtype and grouped gemm. Most importantly, it is required for our new preshuffled mixed dtype kernels. This diff also includes compatibility fixes across the codebase such as in Machete and indexing operations of FBGEMM.

Differential Revision: D69890673

Copy link

netlify bot commented Mar 5, 2025

Deploy Preview for pytorch-fbgemm-docs ready!

Name Link
🔨 Latest commit 3bed952
🔍 Latest deploy log https://app.netlify.com/sites/pytorch-fbgemm-docs/deploys/67c7dca58b758800088d1695
😎 Deploy Preview https://deploy-preview-3767--pytorch-fbgemm-docs.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69890673

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69890673

@jwfromm jwfromm force-pushed the export-D69890673 branch from 07bdaf5 to 12ca989 Compare March 5, 2025 01:57
Summary:
X-link: facebookresearch/FBGEMM#848


Update the Codesign copy of cutlass to version 3.8 V2. This includes new features and changes for mixed dtype and grouped gemm. Most importantly, it is required for our new preshuffled mixed dtype kernels. This diff also includes compatibility fixes across the codebase such as in Machete and indexing operations of FBGEMM.

Reviewed By: jiawenliu64

Differential Revision: D69890673
@jwfromm jwfromm force-pushed the export-D69890673 branch from 12ca989 to 123144e Compare March 5, 2025 04:59
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D69890673

@jwfromm jwfromm requested a review from q10 March 5, 2025 05:11
jwfromm added a commit to jwfromm/FBGEMM that referenced this pull request Mar 5, 2025
Summary:
X-link: facebookresearch/FBGEMM#848


Update the Codesign copy of cutlass to version 3.8 V2. This includes new features and changes for mixed dtype and grouped gemm. Most importantly, it is required for our new preshuffled mixed dtype kernels. This diff also includes compatibility fixes across the codebase such as in Machete and indexing operations of FBGEMM.

Reviewed By: q10, jiawenliu64

Differential Revision: D69890673
jwfromm added a commit to jwfromm/FBGEMM that referenced this pull request Mar 5, 2025
Summary:
X-link: facebookresearch/FBGEMM#848


Update the Codesign copy of cutlass to version 3.8 V2. This includes new features and changes for mixed dtype and grouped gemm. Most importantly, it is required for our new preshuffled mixed dtype kernels. This diff also includes compatibility fixes across the codebase such as in Machete and indexing operations of FBGEMM.

Reviewed By: q10, jiawenliu64

Differential Revision: D69890673
jwfromm pushed a commit to jwfromm/FBGEMM that referenced this pull request Mar 5, 2025
Summary:
X-link: facebookresearch/FBGEMM#848

Pull Request resolved: pytorch#3767

Update the Codesign copy of cutlass to version 3.8 V2. This includes new features and changes for mixed dtype and grouped gemm. Most importantly, it is required for our new preshuffled mixed dtype kernels. This diff also includes compatibility fixes across the codebase such as in Machete and indexing operations of FBGEMM.

Differential Revision: D69890673

Reviewed By: q10, jiawenliu64
@facebook-github-bot
Copy link
Contributor

This pull request has been merged in d162e6e.

jwfromm added a commit to jwfromm/FBGEMM that referenced this pull request Mar 6, 2025
Summary:
pytorch#3767 updated APIs for cutlass 3.8 but due to fun phabricator <-> github issues did not properly bump the OSS version of cutlass. This small change does that.

Pull Request resolved: pytorch#3772

Differential Revision: D70678817

Pulled By: jwfromm
facebook-github-bot pushed a commit that referenced this pull request Mar 6, 2025
Summary:
X-link: facebookresearch/FBGEMM#856

#3767 updated APIs for cutlass 3.8 but due to fun phabricator <-> github issues did not properly bump the OSS version of cutlass. This small change does that.

Pull Request resolved: #3772

Reviewed By: q10

Differential Revision: D70678817

Pulled By: jwfromm

fbshipit-source-id: a82ea3a5a28e12820d0736136cb43f183b4de1af
q10 pushed a commit to q10/FBGEMM that referenced this pull request Apr 10, 2025
Summary:
Pull Request resolved: facebookresearch/FBGEMM#848

X-link: pytorch#3767

Update the Codesign copy of cutlass to version 3.8 V2. This includes new features and changes for mixed dtype and grouped gemm. Most importantly, it is required for our new preshuffled mixed dtype kernels. This diff also includes compatibility fixes across the codebase such as in Machete and indexing operations of FBGEMM.

Reviewed By: q10, jiawenliu64

Differential Revision: D69890673

fbshipit-source-id: 5aad55321c3adb9d82fc1b76dad727943b17fee3
q10 pushed a commit to q10/FBGEMM that referenced this pull request Apr 10, 2025
Summary:
Pull Request resolved: facebookresearch/FBGEMM#856

pytorch#3767 updated APIs for cutlass 3.8 but due to fun phabricator <-> github issues did not properly bump the OSS version of cutlass. This small change does that.

X-link: pytorch#3772

Reviewed By: q10

Differential Revision: D70678817

Pulled By: jwfromm

fbshipit-source-id: a82ea3a5a28e12820d0736136cb43f183b4de1af
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants