search

pytorch / FBGEMM

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
Other
1.12k stars 451 forks source link

Only scaling at boundary. #2801

Closed htyu closed 2 weeks ago

htyu commented 2 weeks ago

Summary: Taking advantage of that scale_block_k is always a multiple of BLOCK_K we can avoid scaling for every K-block and only scale at the boundary. This also allows for a cheaper arithmetic check.

Differential Revision: D59248142

netlify[bot] commented 2 weeks ago

Deploy Preview for pytorch-fbgemm-docs ready!

Name Link
Latest commit ad76956cf79f118bf37aa147b5846219f85b8dfc
Latest deploy log https://app.netlify.com/sites/pytorch-fbgemm-docs/deploys/66839e237ecdb20008c67563
Deploy Preview https://deploy-preview-2801--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 2 weeks ago

This pull request was exported from Phabricator. Differential Revision: D59248142

facebook-github-bot commented 2 weeks ago

This pull request was exported from Phabricator. Differential Revision: D59248142

facebook-github-bot commented 2 weeks ago

This pull request was exported from Phabricator. Differential Revision: D59248142

facebook-github-bot commented 2 weeks ago

This pull request was exported from Phabricator. Differential Revision: D59248142

facebook-github-bot commented 2 weeks ago

This pull request has been merged in pytorch/FBGEMM@4844ffd4cfab879276cec3861909b82a462a2d08.