Skip to content
Code Coverage

CUDA: faster q2_K, q3_K MMQ + int8 tensor cores #13224

Sign in to view logs

CUDA: faster q2_K, q3_K MMQ + int8 tensor cores

CUDA: faster q2_K, q3_K MMQ + int8 tensor cores #13224

Triggered via pull request June 14, 2024 14:28
@JohannesGaesslerJohannesGaessler
synchronize #7921
JohannesGaessler:cuda-ptx-mma-17
Status Success
Total duration 48m 47s
Artifacts –

code-coverage.yml

on: pull_request
run
1m 54s
run
Fit to window
Zoom out
Zoom in

Annotations

1 warning
run
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: codecov/codecov-action@v3. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.