Closed htyu closed 2 weeks ago
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...Use your smartphone camera to open QR code link. |
To edit notification comments on pull requests, go to your Netlify site configuration.
This pull request was exported from Phabricator. Differential Revision: D59248142
This pull request was exported from Phabricator. Differential Revision: D59248142
This pull request was exported from Phabricator. Differential Revision: D59248142
This pull request was exported from Phabricator. Differential Revision: D59248142
This pull request has been merged in pytorch/FBGEMM@4844ffd4cfab879276cec3861909b82a462a2d08.
Summary: Taking advantage of that
scale_block_k
is always a multiple ofBLOCK_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