Skip to content

CUDA: add stream-based concurrency (#16991) #31376

CUDA: add stream-based concurrency (#16991)

CUDA: add stream-based concurrency (#16991) #31376

Triggered via push November 30, 2025 00:17
Status Queued
Total duration
Artifacts 1

build.yml

on: push
macOS-latest-cmake-arm64
7m 46s
macOS-latest-cmake-arm64
macOS-latest-cmake-x64
8m 0s
macOS-latest-cmake-x64
macOS-latest-cmake-arm64-webgpu
4m 8s
macOS-latest-cmake-arm64-webgpu
ubuntu-latest-llguidance
4m 45s
ubuntu-latest-llguidance
ubuntu-latest-cmake-rpc
4m 17s
ubuntu-latest-cmake-rpc
ubuntu-24-cmake-vulkan-deb
2m 2s
ubuntu-24-cmake-vulkan-deb
ubuntu-24-cmake-vulkan
1h 7m
ubuntu-24-cmake-vulkan
ubuntu-24-cmake-webgpu
6m 33s
ubuntu-24-cmake-webgpu
ubuntu-22-cmake-hip
10m 21s
ubuntu-22-cmake-hip
ubuntu-22-cmake-musa
17m 32s
ubuntu-22-cmake-musa
ubuntu-22-cmake-sycl
2m 44s
ubuntu-22-cmake-sycl
ubuntu-22-cmake-sycl-fp16
2m 27s
ubuntu-22-cmake-sycl-fp16
build-linux-cross  /  debian-13-loongarch64-cpu-cross
4m 1s
build-linux-cross / debian-13-loongarch64-cpu-cross
build-linux-cross  /  debian-13-loongarch64-vulkan-cross
7m 2s
build-linux-cross / debian-13-loongarch64-vulkan-cross
build-linux-cross  /  ubuntu-24-riscv64-cpu-spacemit-ime-cross
4m 25s
build-linux-cross / ubuntu-24-riscv64-cpu-spacemit-ime-cross
build-cmake-pkg  /  linux
4m 42s
build-cmake-pkg / linux
macOS-latest-cmake-ios
1m 39s
macOS-latest-cmake-ios
macOS-latest-cmake-tvos
1m 33s
macOS-latest-cmake-tvos
macOS-latest-cmake-visionos
1m 46s
macOS-latest-cmake-visionos
ubuntu-latest-cmake-cuda
12m 26s
ubuntu-latest-cmake-cuda
windows-latest-cmake-sycl
7m 51s
windows-latest-cmake-sycl
windows-latest-cmake-hip
11m 15s
windows-latest-cmake-hip
android-build
12m 9s
android-build
ggml-ci-x64-cpu-low-perf
3m 38s
ggml-ci-x64-cpu-low-perf
ggml-ci-arm64-cpu-low-perf
3m 15s
ggml-ci-arm64-cpu-low-perf
ggml-ci-x64-cpu-high-perf
15m 53s
ggml-ci-x64-cpu-high-perf
ggml-ci-arm64-cpu-high-perf
11m 58s
ggml-ci-arm64-cpu-high-perf
ggml-ci-arm64-cpu-high-perf-sve
11m 40s
ggml-ci-arm64-cpu-high-perf-sve
ggml-ci-x64-nvidia-cuda
12m 48s
ggml-ci-x64-nvidia-cuda
ggml-ci-x64-nvidia-vulkan-cm
22m 26s
ggml-ci-x64-nvidia-vulkan-cm
ggml-ci-x64-nvidia-vulkan-cm2
27m 16s
ggml-ci-x64-nvidia-vulkan-cm2
ggml-ci-x64-cpu-amx
15m 6s
ggml-ci-x64-cpu-amx
ggml-ci-x64-amd-vulkan
ggml-ci-x64-amd-vulkan
ggml-ci-x64-amd-rocm
ggml-ci-x64-amd-rocm
ggml-ci-mac-metal
7m 0s
ggml-ci-mac-metal
ggml-ci-mac-vulkan
8m 34s
ggml-ci-mac-vulkan
ggml-ci-arm64-cpu-kleidiai
21m 58s
ggml-ci-arm64-cpu-kleidiai
ggml-ci-arm64-graviton4-kleidiai
7m 38s
ggml-ci-arm64-graviton4-kleidiai
Matrix: android-ndk-build
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
Fit to window
Zoom out
Zoom in

Annotations

1 error and 8 warnings
ggml-ci-mac-vulkan
Process completed with exit code 8.
macOS-latest-cmake-tvos
Cache not found for keys: ccache-macOS-latest-cmake-tvos-
windows-msys2 (UCRT64, ucrt-x86_64, Release)
Cache not found for keys: ccache-windows-msys2-
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-cmake-ios
Cache not found for keys: ccache-macOS-latest-cmake-ios-
windows-msys2 (CLANG64, clang-x86_64, Release)
Cache not found for keys: ccache-windows-msys2-
macOS-latest-swift (generic/platform=macOS)
Cache not found for keys: ccache-macOS-latest-swift-
macOS-latest-swift (generic/platform=tvOS)
Cache not found for keys: ccache-macOS-latest-swift-
macOS-latest-swift (generic/platform=iOS)
Cache not found for keys: ccache-macOS-latest-swift-

Artifacts

Produced during runtime
Name Size Digest
llama-xcframework
146 MB
sha256:be0a6b88935ac15ffe6d29f8bf9affc76b78965b0955f428e2a17d7860d84ed9