Files
koboldcpp/.github/workflows/build-vulkan.yml
T
Georgi Gerganov b78a39a2f9 ci : run test-backend-ops as a dedicated ci/run.sh test (#28740)
* ci : run test-backend-ops as a dedicated gg test

Run test-backend-ops as a separate gg test in ci/run.sh so it is executed outside ctest. With GG_BUILD_HIGH_PERF it keeps the existing CPU-only invocation (-b CPU); otherwise it runs all available backends without a backend filter.

Remove the dedicated backend-ops workflow and keep test-backend-ops as a built target that is not registered with ctest to avoid duplicate runs.

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* ci : run test-backend-ops earlier and enable high-perf on kleidiai

Move the test-backend-ops gg test before test-llama-archs.

Enable GG_BUILD_HIGH_PERF and LLAMA_ARG_THREADS on the Graviton4 KleidiAI job and use the standard self-hosted results/mnt paths.

Add TODO markers for decoupling tests from libllama.

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* ci : run test-backend-ops in parallel

Pass -j $(nproc) to test-backend-ops in both high-perf and all-backend modes.

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* ci : disable parallel tests for ROCm

* cont : disable parallel tests with MoltenVK
2026-09-11 22:00:57 +03:00

231 lines
6.4 KiB
YAML

name: CI (vulkan)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-vulkan.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.comp',
'**/*.glsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-vulkan.yml',
'ggml/src/ggml-vulkan/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-arm64:
runs-on: ubuntu-24.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y gcc-14 g++-14 build-essential glslc libvulkan-dev spirv-headers libssl-dev ninja-build
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
key: vulkan-ubuntu-24.04-arm
variant: ccache
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: vulkan-ubuntu-24.04-arm
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Configure
id: cmake_configure
run: |
cmake -B build \
-G "Ninja" \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_VULKAN=ON
- name: Build
id: cmake_build
run: |
time cmake --build build -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: vulkan-ubuntu-24.04-arm
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
ubuntu-llvmpipe:
runs-on: ubuntu-24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo add-apt-repository -y ppa:kisak/kisak-mesa
sudo apt-get update -y
sudo apt-get install -y build-essential mesa-vulkan-drivers libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
- name: Get latest Vulkan SDK version
id: vulkan_sdk_version
run: |
echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
- name: Setup Vulkan SDK
id: setup
uses: ./.github/actions/unarchive-tar
with:
url: https://sdk.lunarg.com/sdk/download/${{ env.VULKAN_SDK_VERSION }}/linux/vulkan_sdk.tar.xz
path: ./vulkan_sdk
strip: 1
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
key: vulkan-ubuntu-24.04-llvmpipe
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: vulkan-ubuntu-24.04-llvmpipe
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
id: cmake_build
run: |
source ./vulkan_sdk/setup-env.sh
cmake -B build \
-DGGML_NATIVE=OFF \
-DGGML_VULKAN=ON
cmake --build build --config Release -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: vulkan-ubuntu-24.04-llvmpipe
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Test
id: cmake_test
run: |
cd build
export GGML_VK_VISIBLE_DEVICES=0
export GGML_VK_DISABLE_F16=1
export GGML_VK_DISABLE_COOPMAT=1
ctest -L main --verbose --timeout 900
windows:
runs-on: windows-2025
env:
VULKAN_VERSION: 1.4.357.0
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
key: cpu-windows-2025-x64-vulkan
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Install Vulkan SDK
id: get_vulkan
run: |
curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
& "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Build
id: cmake_build
run: |
cmake -S . -B build -G "Ninja Multi-Config" `
-D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake `
-DCMAKE_BUILD_TYPE=Release `
-DGGML_NATIVE=OFF `
-DLLAMA_BUILD_SERVER=ON `
-DGGML_RPC=ON `
-DGGML_BACKEND_DL=ON `
-DGGML_CPU_ALL_VARIANTS=ON `
-DGGML_VULKAN=ON `
-DLLAMA_BUILD_BORINGSSL=ON
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Test
id: cmake_test
run: |
cd build
ctest -L main -C Release --verbose --timeout 900
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: cpu-windows-2025-x64-vulkan
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}