Bumping flash attention version to 2.6.3 and adding option for softcap in attention and lm_head logits. #7148
Annotations
2 warnings
|
The following actions uses Node.js version which is deprecated and will be forced to run on node20: actions/checkout@v3, actions/upload-artifact@v3. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
|
|
The following artifacts were uploaded using a version of actions/upload-artifact that is scheduled for deprecation: "coverage-0e1cc9745ea41dd88b135d6aecbf51c44768421a-cpu-2.3.1".
Please update your workflow to use v4 of the artifact actions.
Learn more: https://github.blog/changelog/2024-04-16-deprecation-notice-v3-of-the-artifact-actions/
|
This job succeeded
Loading