Skip to content

feat: flash attention in model selection #535

feat: flash attention in model selection

feat: flash attention in model selection #535

Triggered via pull request July 5, 2024 23:57
Status Success
Total duration 1h 22m 17s
Artifacts 7

build.yml

on: pull_request
Matrix: build-binaries
Standalone tests
1m 35s
Standalone tests
Model dependent tests
1h 20m
Model dependent tests
Release
0s
Release
Matrix: build-electron-example
Fit to window
Zoom out
Zoom in

Annotations

4 warnings
Build binaries - macOS
Treating cmake as a formula. For the cask, use homebrew/cask/cmake or specify the `--cask` flag.
Model dependent tests
Treating cmake as a formula. For the cask, use homebrew/cask/cmake or specify the `--cask` flag.
Model dependent tests
cmake 3.29.6 is already installed and up-to-date. To reinstall 3.29.6, run: brew reinstall cmake
Model dependent tests
Failed to save: Cache size of ~10748 MB (11269848295 B) is over the 10GB limit, not saving cache.

Artifacts

Produced during runtime
Name Size
bins-linux
98.9 MB
bins-mac
2.41 MB
bins-win-arm
851 KB
bins-win-x64
94.7 MB
build
541 KB
build-templates
22.8 KB
llama.cpp
63.4 MB