Skip to content

[llama-mm] Enable kv cache for MultiHeadAttention #101

[llama-mm] Enable kv cache for MultiHeadAttention

[llama-mm] Enable kv cache for MultiHeadAttention #101

Triggered via pull request November 12, 2024 22:17
Status Success
Total duration 34s
Artifacts

ghstack_land.yml

on: pull_request
Try to create a PR with ghstack /orig branch
21s
Try to create a PR with ghstack /orig branch
Fit to window
Zoom out
Zoom in

Annotations

1 warning
Try to create a PR with ghstack /orig branch
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/checkout@v3, actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/