CPU/CUDA: Gemma 2 FlashAttention support (#8542) #2
build.yml
on: push
Matrix: windows-latest-cmake-cuda
Matrix: windows-latest-cmake
macOS-latest-cmake-arm64
2m 23s
macOS-latest-cmake-x64
8m 56s
ubuntu-focal-make
3m 48s
ubuntu-latest-cmake
2m 44s
macOS-latest-make
2m 10s
macOS-latest-cmake
1m 44s
ubuntu-focal-make-curl
3m 0s
ubuntu-latest-cmake-rpc
2m 20s
ubuntu-22-cmake-vulkan
3m 2s
ubuntu-22-cmake-hip
18m 9s
ubuntu-22-cmake-sycl
10m 1s
ubuntu-22-cmake-sycl-fp16
10m 20s
macOS-latest-cmake-ios
2m 17s
macOS-latest-cmake-tvos
2m 5s
windows-latest-cmake-sycl
11m 26s
windows-latest-cmake-hip
14m 14s
ios-xcode-build
1m 29s
android-build
15m 38s
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-sanitizer
Matrix: windows-msys2
release
47s
Annotations
1 error and 9 warnings
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
|
48.4 MB |
|
llama-bin-macos-x64.zip
|
50 MB |
|
llama-bin-ubuntu-x64.zip
|
54 MB |
|
llama-bin-win-avx-x64.zip
|
7.65 MB |
|
llama-bin-win-avx2-x64.zip
|
7.65 MB |
|
llama-bin-win-avx512-x64.zip
|
7.65 MB |
|
llama-bin-win-cu11.7.1-x64.zip
|
143 MB |
|
llama-bin-win-cu12.2.0-x64.zip
|
142 MB |
|
llama-bin-win-kompute-x64.zip
|
7.92 MB |
|
llama-bin-win-llvm-arm64.zip
|
11.1 MB |
|
llama-bin-win-msvc-arm64.zip
|
13.2 MB |
|
llama-bin-win-noavx-x64.zip
|
7.64 MB |
|
llama-bin-win-openblas-x64.zip
|
18.6 MB |
|
llama-bin-win-sycl-x64.zip
|
68.6 MB |
|
llama-bin-win-vulkan-x64.zip
|
8.24 MB |
|