llama : add --no-host to disable host buffers (#16310) #237
build.yml
on: push
ios-xcode-build
18m 51s
macOS-latest-cmake-arm64
5m 17s
macOS-latest-cmake-x64
11m 24s
macOS-latest-cmake-arm64-webgpu
8m 11s
ubuntu-latest-llguidance
6m 22s
ubuntu-latest-cmake-rpc
5m 11s
ubuntu-24-cmake-vulkan
45m 6s
ubuntu-22-cmake-webgpu
8m 44s
ubuntu-22-cmake-hip
10m 42s
ubuntu-22-cmake-musa
17m 53s
ubuntu-22-cmake-sycl
9m 29s
ubuntu-22-cmake-sycl-fp16
7m 34s
build-linux-cross
/
ubuntu-24-riscv64-cpu-cross
5m 29s
build-linux-cross
/
debian-13-loongarch64-cpu-cross
3m 33s
build-linux-cross
/
debian-13-loongarch64-vulkan-cross
6m 5s
build-linux-cross
/
ubuntu-24-riscv64-cpu-spacemit-ime-cross
5m 9s
build-cmake-pkg
/
linux
4m 5s
macOS-latest-cmake-ios
2m 15s
macOS-latest-cmake-tvos
1m 21s
macOS-latest-cmake-visionos
1m 16s
ubuntu-latest-cmake-cuda
14m 16s
windows-latest-cmake-sycl
13m 48s
windows-latest-cmake-hip
12m 30s
android-build
10m 14s
ggml-ci-x64-cpu-low-perf
7m 15s
ggml-ci-arm64-cpu-low-perf
5m 59s
ggml-ci-x64-cpu-high-perf
20m 15s
ggml-ci-arm64-cpu-high-perf
16m 1s
ggml-ci-arm64-cpu-high-perf-sve
15m 8s
ggml-ci-x64-nvidia-cuda
1d 0h
ggml-ci-x64-nvidia-vulkan-cm
0s
ggml-ci-x64-nvidia-vulkan-cm2
0s
ggml-ci-x64-cpu-amx
1d 0h
ggml-ci-mac-metal
1d 0h
ggml-ci-mac-vulkan
0s
Matrix: openEuler-latest-cmake-cann
Matrix: ubuntu-cpu-cmake
Matrix: ubuntu-latest-cmake-sanitizer
Matrix: windows-2022-cmake-cuda
Matrix: windows-latest-cmake
Matrix: windows-msys2
Matrix: macOS-latest-swift
Annotations
8 errors and 12 warnings
ubuntu-cpu-cmake (ppc64le, ubuntu-24.04-ppc64le)
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
ubuntu-cpu-cmake (s390x, ubuntu-24.04-s390x)
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
ggml-ci-mac-vulkan
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
ggml-ci-x64-nvidia-vulkan-cm2
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
ggml-ci-x64-nvidia-cuda
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
ggml-ci-mac-metal
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
ggml-ci-x64-cpu-amx
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
ggml-ci-x64-nvidia-vulkan-cm
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
windows-msys2 (CLANG64, clang-x86_64, Release)
Cache not found for keys: ccache-windows-msys2-
|
macOS-latest-cmake-arm64-webgpu
curl 8.16.0 is already installed and up-to-date.
To reinstall 8.16.0, run:
brew reinstall curl
|
macOS-latest-cmake-arm64
curl 8.16.0 is already installed and up-to-date.
To reinstall 8.16.0, run:
brew reinstall curl
|
macOS-latest-cmake-ios
Cache not found for keys: ccache-macOS-latest-cmake-ios-
|
windows-msys2 (UCRT64, ucrt-x86_64, Release)
Cache not found for keys: ccache-windows-msys2-
|
macOS-latest-cmake-tvos
Cache not found for keys: ccache-macOS-latest-cmake-tvos-
|
macOS-latest-cmake-x64
curl 8.16.0 is already installed and up-to-date.
To reinstall 8.16.0, run:
brew reinstall curl
|
windows-latest-cmake (vulkan-x64, x64, -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD...
Cache not found for keys: ccache-windows-latest-cmake-vulkan-x64-
|
macOS-latest-swift (generic/platform=tvOS)
Cache not found for keys: ccache-macOS-latest-swift-
|
macOS-latest-swift (generic/platform=macOS)
Cache not found for keys: ccache-macOS-latest-swift-
|
macOS-latest-swift (generic/platform=iOS)
Cache not found for keys: ccache-macOS-latest-swift-
|
ubuntu-24-cmake-vulkan
Cache not found for keys: ccache-ubuntu-24-cmake-vulkan-
|
Artifacts
Produced during runtime
Name | Size | Digest | |
---|---|---|---|
llama-xcframework
Expired
|
92.4 MB |
sha256:ee055994032b312227fc0fd992c3104b87aa547ca1c00c48271e9b290a476867
|
|