vulkan: Optimize some mat-vec mul quant shaders (#10296) #16742
build.yml
on: push
Matrix: windows-latest-cmake-cuda
Matrix: windows-latest-cmake-hip-release
Matrix: windows-latest-cmake
macOS-latest-cmake-arm64
12m 6s
macOS-latest-cmake-x64
3m 42s
ubuntu-focal-make
3m 19s
ubuntu-latest-cmake
3m 15s
macOS-latest-make
2m 4s
macOS-latest-cmake
11m 11s
ubuntu-focal-make-curl
2m 31s
ubuntu-latest-cmake-rpc
2m 16s
ubuntu-22-cmake-vulkan
3m 1s
ubuntu-22-cmake-hip
18m 6s
ubuntu-22-cmake-musa
11m 45s
ubuntu-22-cmake-sycl
4m 40s
ubuntu-22-cmake-sycl-fp16
4m 48s
macOS-latest-cmake-ios
1m 44s
macOS-latest-cmake-tvos
1m 42s
windows-latest-cmake-sycl
11m 30s
windows-latest-cmake-hip
29m 19s
ios-xcode-build
1m 40s
android-build
5m 47s
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-sanitizer
Matrix: windows-msys2
release
2m 3s
Annotations
2 errors and 3 warnings
windows-latest-cmake (avx512-x64, -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_...
Process completed with exit code 1.
|
windows-latest-cmake-sycl
Process completed with exit code 1.
|
android-build
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-java@v3. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
|
release
The following actions uses node12 which is deprecated and will be forced to run on node16: actions/github-script@v3. For more info: https://github.blog/changelog/2023-06-13-github-actions-all-actions-will-run-on-node16-instead-of-node12-by-default/
|
release
The following actions use a deprecated Node.js version and will be forced to run on node20: anzz1/action-create-release@v1, actions/github-script@v3. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
|
Artifacts
Produced during runtime
Name | Size | |
---|---|---|
cudart-llama-bin-win-cu11.7.1-x64.zip
|
293 MB |
|
cudart-llama-bin-win-cu12.2.0-x64.zip
|
412 MB |
|
llama-bin-macos-arm64.zip
|
51.3 MB |
|
llama-bin-macos-x64.zip
|
52.2 MB |
|
llama-bin-ubuntu-x64.zip
|
56.5 MB |
|
llama-bin-win-avx-x64.zip
|
8.13 MB |
|
llama-bin-win-avx2-x64.zip
|
8.14 MB |
|
llama-bin-win-avx512-x64.zip
|
8.14 MB |
|
llama-bin-win-cu11.7.1-x64.zip
|
147 MB |
|
llama-bin-win-cu12.2.0-x64.zip
|
146 MB |
|
llama-bin-win-hip-x64-gfx1030.zip
|
228 MB |
|
llama-bin-win-hip-x64-gfx1100.zip
|
230 MB |
|
llama-bin-win-hip-x64-gfx1101.zip
|
230 MB |
|
llama-bin-win-kompute-x64.zip
|
8.43 MB |
|
llama-bin-win-llvm-arm64.zip
|
9.85 MB |
|
llama-bin-win-msvc-arm64.zip
|
12.1 MB |
|
llama-bin-win-noavx-x64.zip
|
8.11 MB |
|
llama-bin-win-openblas-x64.zip
|
19.1 MB |
|
llama-bin-win-vulkan-x64.zip
|
8.77 MB |
|