Skip to content

use flash_attn_with_kvcache for faster inference #1318

use flash_attn_with_kvcache for faster inference

use flash_attn_with_kvcache for faster inference #1318

Triggered via pull request December 19, 2023 15:57
Status Success
Total duration 5m 1s
Artifacts

push.yml

on: pull_request
Matrix: lint-and-tests
Fit to window
Zoom out
Zoom in

Annotations

2 warnings
build-docs
The following actions uses node12 which is deprecated and will be forced to run on node16: actions/checkout@v2, actions/setup-python@v2. For more info: https://github.blog/changelog/2023-06-13-github-actions-all-actions-will-run-on-node16-instead-of-node12-by-default/
lint-and-tests (3.8)
The following actions uses node12 which is deprecated and will be forced to run on node16: actions/checkout@v2, actions/setup-python@v2. For more info: https://github.blog/changelog/2023-06-13-github-actions-all-actions-will-run-on-node16-instead-of-node12-by-default/