From 0e861f79a30e6a111d14cac1c5ba5d915a3ce773 Mon Sep 17 00:00:00 2001 From: yomaytk Date: Wed, 29 Jul 2026 11:14:22 +0900 Subject: [PATCH] try to use gpu-webgpu-intel in ci --- .github/workflows/build-self-hosted.yml | 328 +----------------------- 1 file changed, 4 insertions(+), 324 deletions(-) diff --git a/.github/workflows/build-self-hosted.yml b/.github/workflows/build-self-hosted.yml index 0ef202193c78..88099bbf749d 100644 --- a/.github/workflows/build-self-hosted.yml +++ b/.github/workflows/build-self-hosted.yml @@ -57,75 +57,15 @@ env: LLAMA_ARG_LOG_TIMESTAMPS: 1 jobs: - gpu-cuda: - runs-on: [self-hosted, Linux, NVIDIA] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - nvidia-smi - GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-rocm: - runs-on: [self-hosted, Linux, AMD] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - # HIP_LAUNCH_BLOCKING=1: workaround for an async-execution correctness - # issue on integrated RDNA3.5 (gfx1151) where batched inference returns - # incorrect output (perplexity ~88 vs ~9.4). Serializing kernel launches - # restores correctness. Remove once the underlying ROCm/HIP issue is fixed. - env: - HIP_LAUNCH_BLOCKING: "1" - run: | - rocminfo - GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS=gfx1151 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-vulkan-nvidia-cm: - runs-on: [self-hosted, Linux, NVIDIA] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - vulkaninfo --summary - GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-vulkan-nvidia-cm2: - runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - vulkaninfo --summary - GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-webgpu-nvidia: - runs-on: [self-hosted, Linux, NVIDIA, X64] + gpu-webgpu-intel: + runs-on: [self-hosted, Linux, Intel, X64] steps: - name: Clone id: checkout uses: actions/checkout@v6 + with: + persist-credentials: false - name: Dawn Dependency id: dawn-depends @@ -147,263 +87,3 @@ jobs: GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \ GG_BUILD_WEBGPU_DAWN_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \ bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - # TODO: provision AMX-compatible machine - #cpu-amx: - # runs-on: [self-hosted, Linux, CPU, AMX] - - # steps: - # - name: Clone - # id: checkout - # uses: actions/checkout@v6 - - # - name: Test - # id: ggml-ci - # run: | - # bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - # TODO: provision AMD GPU machine - # amd-vulkan: - # runs-on: [self-hosted, Linux, AMD] - - # steps: - # - name: Clone - # id: checkout - # uses: actions/checkout@v6 - - # - name: Test - # id: ggml-ci - # run: | - # vulkaninfo --summary - # GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - # TODO: provision AMD GPU machine - # amd-rocm: - # runs-on: [self-hosted, Linux, AMD] - - # steps: - # - name: Clone - # id: checkout - # uses: actions/checkout@v6 - - # - name: Test - # id: ggml-ci - # run: | - # amd-smi static - # GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-metal: - runs-on: [self-hosted, macOS, ARM64] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-webgpu-apple: - runs-on: [self-hosted, macOS, ARM64] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Dawn Dependency - id: dawn-depends - run: | - DAWN_VERSION="v20260317.182325" - DAWN_OWNER="google" - DAWN_REPO="dawn" - DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release" - echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" - curl -L -o artifact.tar.gz \ - "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz" - mkdir dawn - tar -xvf artifact.tar.gz -C dawn --strip-components=1 - - - name: Test - id: ggml-ci - run: | - GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \ - bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-vulkan-apple: - runs-on: [self-hosted, macOS, ARM64] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - vulkaninfo --summary - GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-vulkan-intel-linux: - runs-on: [self-hosted, Linux, Intel] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - with: - persist-credentials: false - - - name: Test - id: ggml-ci - run: | - vulkaninfo --summary - GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - gpu-vulkan-intel-windows: - runs-on: [self-hosted, Windows, X64, Intel] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - shell: C:\msys64\usr\bin\bash.exe --noprofile --norc -eo pipefail "{0}" - env: - MSYSTEM: UCRT64 - CHERE_INVOKING: 1 - PATH: C:\msys64\ucrt64\bin;C:\msys64\usr\bin;C:\Windows\System32;${{ env.PATH }} - run: | - vulkaninfo --summary - # Skip python related tests with GG_BUILD_LOW_PERF=1 since Windows MSYS2 UCRT64 currently fails to create - # a valid python environment for testing - LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp - - gpu-openvino-low-perf: - runs-on: [self-hosted, Linux, Intel, OpenVINO] - - env: - # Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile - OPENVINO_VERSION_MAJOR: "2026.2.1" - OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3" - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Setup OpenVINO Toolkit - uses: ./.github/actions/linux-setup-openvino - with: - path: ./openvino_toolkit - version_major: ${{ env.OPENVINO_VERSION_MAJOR }} - version_full: ${{ env.OPENVINO_VERSION_FULL }} - - - name: Install OpenVINO dependencies - run: | - cd ./openvino_toolkit - chmod +x ./install_dependencies/install_openvino_dependencies.sh - echo "Y" | sudo -E ./install_dependencies/install_openvino_dependencies.sh - - - name: Test - id: ggml-ci - run: | - source ./openvino_toolkit/setupvars.sh - GG_BUILD_OPENVINO=1 GGML_OPENVINO_DEVICE=GPU GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - cpu-x64-high-perf: - runs-on: [self-hosted, Linux, X64] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - cpu-arm64-high-perf-graviton4: - runs-on: ah-ubuntu_22_04-c8g_8x - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Dependencies - id: depends - run: | - set -euxo pipefail - sudo apt-get update - sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \ - apt-get install -y \ - build-essential \ - python3-venv \ - gpg \ - wget \ - time \ - git-lfs - - git lfs install - - # install the latest cmake - sudo install -d /usr/share/keyrings - wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \ - | gpg --dearmor \ - | sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null - echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \ - | sudo tee /etc/apt/sources.list.d/kitware.list - sudo apt-get update - sudo apt-get install -y cmake - - - name: Test - id: ggml-ci - run: | - LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp - - cpu-arm64-graviton4-kleidiai: - runs-on: ah-ubuntu_22_04-c8g_8x - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Dependencies - id: depends - run: | - set -euxo pipefail - sudo apt-get update - sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \ - apt-get install -y \ - build-essential \ - python3-venv \ - gpg \ - wget \ - time \ - git-lfs - - git lfs install - - # install the latest cmake - sudo install -d /usr/share/keyrings - wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \ - | gpg --dearmor \ - | sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null - echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \ - | sudo tee /etc/apt/sources.list.d/kitware.list - sudo apt-get update - sudo apt-get install -y cmake - - - name: Test - id: ggml-ci - run: | - GG_BUILD_KLEIDIAI=1 \ - GG_BUILD_EXTRA_TESTS_0=1 \ - bash ./ci/run.sh ./tmp/results ./tmp/mnt