CPU/CUDA: fix (GQA) mul mat back, add CUDA support (#11380) #18
fairydreamingbuild.yml
on: push
Matrix: windows-2019-cmake-cuda
Matrix: windows-latest-cmake-hip-release
Matrix: windows-latest-cmake
macOS-latest-cmake-arm64
12m 56s
macOS-latest-cmake-x64
6m 15s
ubuntu-latest-cmake
3m 5s
macOS-latest-cmake
12m 24s
ubuntu-latest-cmake-rpc
2m 43s
ubuntu-22-cmake-vulkan
18m 35s
ubuntu-22-cmake-hip
20m 23s
ubuntu-22-cmake-musa
12m 28s
ubuntu-22-cmake-sycl
5m 5s
ubuntu-22-cmake-sycl-fp16
5m 8s
macOS-latest-cmake-ios
1m 25s
macOS-latest-cmake-tvos
1m 39s
ubuntu-latest-cmake-cuda
11m 52s
windows-latest-cmake-sycl
11m 29s
windows-latest-cmake-hip
26m 42s
ios-xcode-build
1m 25s
android-build
8m 11s
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-sanitizer
Matrix: windows-msys2
release
2m 15s
Annotations
1 error and 8 warnings
Artifacts
Produced during runtime
| Name | Size | |
|---|---|---|
|
cudart-llama-bin-win-cu11.7-x64.zip
|
303 MB |
|
|
cudart-llama-bin-win-cu12.4-x64.zip
|
372 MB |
|
|
llama-bin-macos-arm64.zip
|
19.8 MB |
|
|
llama-bin-macos-x64.zip
|
21.3 MB |
|
|
llama-bin-ubuntu-x64.zip
|
23.1 MB |
|
|
llama-bin-win-avx-x64.zip
|
13.8 MB |
|
|
llama-bin-win-avx2-x64.zip
|
13.8 MB |
|
|
llama-bin-win-avx512-x64.zip
|
13.8 MB |
|
|
llama-bin-win-cu11.7-x64.zip
|
150 MB |
|
|
llama-bin-win-cu12.4-x64.zip
|
150 MB |
|
|
llama-bin-win-hip-x64-gfx1030.zip
|
236 MB |
|
|
llama-bin-win-hip-x64-gfx1100.zip
|
238 MB |
|
|
llama-bin-win-hip-x64-gfx1101.zip
|
238 MB |
|
|
llama-bin-win-kompute-x64.zip
|
14.1 MB |
|
|
llama-bin-win-llvm-arm64-opencl-adreno.zip
|
17.5 MB |
|
|
llama-bin-win-llvm-arm64.zip
|
17.5 MB |
|
|
llama-bin-win-msvc-arm64.zip
|
56.4 MB |
|
|
llama-bin-win-noavx-x64.zip
|
13.8 MB |
|
|
llama-bin-win-openblas-x64.zip
|
24.8 MB |
|
|
llama-bin-win-sycl-x64.zip
|
95.3 MB |
|
|
llama-bin-win-vulkan-x64.zip
|
15.9 MB |
|