search

pytorch / FBGEMM

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
Other
1.17k stars 474 forks source link

Support for other MX4 formats in Triton kernels #2900

Closed jwfromm closed 1 month ago

jwfromm commented 1 month ago

Summary: This diff adds the scaffolding for supporting other MX4 formats. Because we use a lookup table during dequantization, we'll still need to manually enable each combination of ebits and mbits. For now, we add E3M0 support, though it should be easy for us to extend to other formats if needed.

Reviewed By: summerdengfb

Differential Revision: D59887207

netlify[bot] commented 1 month ago

Deploy Preview for pytorch-fbgemm-docs ready!

Name Link
Latest commit d9768c4dd6d593e0f47c0843a88064a38546f6ea
Latest deploy log https://app.netlify.com/sites/pytorch-fbgemm-docs/deploys/66a2b4936322000008d67aab
Deploy Preview https://deploy-preview-2900--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 commented 1 month ago

This pull request was exported from Phabricator. Differential Revision: D59887207

facebook-github-bot commented 1 month ago

This pull request has been merged in pytorch/FBGEMM@8186f52eb2488a8f9762479d05b4ce0e86df67e8.