llama-bench : add test measuring token generation rate at given prompt length #18137
build.yml
on: pull_request
Matrix: windows-2019-cmake-cuda
Matrix: windows-latest-cmake-hip-release
Matrix: windows-latest-cmake
macOS-latest-cmake-arm64
12m 34s
macOS-latest-cmake-x64
7m 18s
ubuntu-latest-cmake
2m 37s
macOS-latest-cmake
11m 44s
ubuntu-latest-cmake-rpc
2m 22s
ubuntu-22-cmake-vulkan
13m 2s
ubuntu-22-cmake-hip
19m 16s
ubuntu-22-cmake-musa
12m 25s
ubuntu-22-cmake-sycl
4m 39s
ubuntu-22-cmake-sycl-fp16
4m 36s
macOS-latest-cmake-ios
1m 29s
macOS-latest-cmake-tvos
1m 13s
ubuntu-latest-cmake-cuda
12m 5s
windows-latest-cmake-sycl
11m 6s
windows-latest-cmake-hip
30m 11s
ios-xcode-build
1m 13s
android-build
6m 39s
Matrix: macOS-latest-swift
Matrix: ubuntu-latest-cmake-sanitizer
Matrix: windows-msys2
release
0s
Annotations
1 error and 10 warnings