Skip to content

Allows interweaving of arbitrary kinds of 'attention' layers, like sliding window, reuse prev layer kv cache etc. #7026

Allows interweaving of arbitrary kinds of 'attention' layers, like sliding window, reuse prev layer kv cache etc.

Allows interweaving of arbitrary kinds of 'attention' layers, like sliding window, reuse prev layer kv cache etc. #7026

Triggered via pull request June 25, 2024 16:42
@ShashankMosaicMLShashankMosaicML
synchronize #1299
Status Failure
Total duration 25m 9s
Artifacts

pr-gpu.yaml

on: pull_request_target
Matrix: pytest-gpu
Fit to window
Zoom out
Zoom in

Annotations

1 error and 2 warnings
gpu-2.3.1 / pytest-gpu
Process completed with exit code 1.
gpu-2.3.0 / pytest-gpu
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions/checkout@v3, actions/setup-python@v4, actions/cache@v3. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.
gpu-2.3.1 / pytest-gpu
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions/checkout@v3, actions/setup-python@v4, actions/cache@v3. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.