mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-27 15:40:50 +02:00
985b14912b
* ci : apply ccache-clear with older/min/dry-run to all ccache jobs Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : install gh in ccache-clear if missing (container jobs) The ccache-clear action relies on the gh CLI, which is not present in container-based jobs. Install it on demand so those jobs can clear caches. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : install gh via apt repo in ccache-clear The install.sh script used previously is no longer served (404). Switch to the official GitHub CLI apt repository, which is still available. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : pass --repo to gh cache commands in ccache-clear In container jobs gh cannot auto-detect the repository from git, so gh cache list/delete fail with 'failed to run git: not a git repository'. Pass the repository explicitly via --repo using GITHUB_REPOSITORY. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : drop -new suffix from vulkan ccache key The -new suffix was only needed to force a fresh cache. With ccache-clear now evicting stale caches, the original key can be used again. The old ccache-vulkan-ubuntu-24.04-arm-new entries still match the ccache-clear key prefix and are cleaned up automatically. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : fix ccache-clear date parsing on macOS (BSD date) macOS ships BSD date, which has no -d option. The older cutoff check was silently disabled there: 'date: illegal option -- d' errors in the log and the loop was only stopped by the min limit, risking deletion of caches not older than the cutoff (e.g. saved by a concurrent job). Parse the ISO-8601 timestamps with GNU date when available and fall back to BSD date otherwise (TZ=UTC, fractional seconds dropped). Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : extract ccache-clear logic into scripts/ccache-clear.sh The composite action now consists of a dedicated step that installs the GitHub CLI when missing (e.g. in container jobs) and a thin step that calls the new script. The script follows the make-release-checks.sh conventions (usage/env header, set -euo pipefail, CLI flags) and only checks that gh is available. The action inputs are unchanged, so the workflow steps are untouched. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731 * ci : remove unused apple ccaches
176 lines
5.3 KiB
YAML
176 lines
5.3 KiB
YAML
name: CI (webgpu)
|
|
|
|
on:
|
|
workflow_dispatch: # allows manual triggering
|
|
push:
|
|
branches:
|
|
- master
|
|
paths: [
|
|
'.github/workflows/build-webgpu.yml',
|
|
'**/CMakeLists.txt',
|
|
'**/.cmake',
|
|
'**/*.h',
|
|
'**/*.hpp',
|
|
'**/*.c',
|
|
'**/*.cpp',
|
|
'**/*.wgsl',
|
|
'**/*.tmpl',
|
|
'ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py'
|
|
]
|
|
|
|
pull_request:
|
|
types: [opened, synchronize, reopened]
|
|
paths: [
|
|
'.github/workflows/build-webgpu.yml',
|
|
'ggml/src/ggml-webgpu/**'
|
|
]
|
|
|
|
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:
|
|
format:
|
|
runs-on: ubuntu-24.04
|
|
|
|
steps:
|
|
- name: Clone
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Install clang-format 22
|
|
run: |
|
|
wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key |
|
|
sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
|
|
sudo add-apt-repository -y \
|
|
"deb http://apt.llvm.org/noble/ llvm-toolchain-noble-22 main"
|
|
sudo apt-get update
|
|
sudo apt-get install -y clang-format-22
|
|
|
|
- name: Check formatting
|
|
run: |
|
|
find ggml/src/ggml-webgpu \
|
|
-type f \( -name '*.cpp' -o -name '*.hpp' -o -name '*.h' \) \
|
|
-print0 |
|
|
xargs -0 clang-format-22 --dry-run --Werror
|
|
|
|
macos:
|
|
runs-on: macos-latest
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: webgpu-macos-latest
|
|
evict-old-files: 1d
|
|
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
|
|
- name: Dawn Dependency
|
|
id: dawn-depends
|
|
run: |
|
|
DAWN_VERSION="v20260317.182325"
|
|
DAWN_OWNER="google"
|
|
DAWN_REPO="dawn"
|
|
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
|
|
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${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: Build
|
|
id: cmake_build
|
|
run: |
|
|
export CMAKE_PREFIX_PATH=dawn
|
|
cmake -B build -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DGGML_WEBGPU=ON -DGGML_METAL=OFF -DGGML_BLAS=OFF
|
|
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
|
|
|
|
- name: Test
|
|
id: cmake_test
|
|
run: |
|
|
cd build
|
|
ctest -L main --verbose --timeout 900
|
|
|
|
- name: ccache-clear
|
|
uses: ./.github/actions/ccache-clear
|
|
env:
|
|
GH_TOKEN: ${{ github.token }}
|
|
with:
|
|
key: webgpu-macos-latest
|
|
older: 5m
|
|
min: 1
|
|
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
|
|
|
|
ubuntu:
|
|
runs-on: ubuntu-24.04
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.21
|
|
with:
|
|
key: webgpu-ubuntu-24.04
|
|
evict-old-files: 1d
|
|
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
|
|
- name: Dependencies
|
|
id: depends
|
|
run: |
|
|
sudo add-apt-repository -y ppa:kisak/kisak-mesa
|
|
sudo apt-get update -y
|
|
sudo apt-get install -y build-essential mesa-vulkan-drivers \
|
|
libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
|
|
|
|
- name: Dawn Dependency
|
|
id: dawn-depends
|
|
run: |
|
|
sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev
|
|
DAWN_VERSION="v20260317.182325"
|
|
DAWN_OWNER="google"
|
|
DAWN_REPO="dawn"
|
|
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
|
|
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${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: Build
|
|
id: cmake_build
|
|
run: |
|
|
export Dawn_DIR=dawn/lib64/cmake/Dawn
|
|
cmake -B build \
|
|
-DGGML_WEBGPU=ON
|
|
time cmake --build build --config Release -j $(nproc)
|
|
|
|
- name: Test
|
|
id: cmake_test
|
|
run: |
|
|
cd build
|
|
# This is using llvmpipe and runs slower than other backends
|
|
# test-backend-ops is too slow on llvmpipe, skip it
|
|
ctest -L main -E test-backend-ops --verbose --timeout 900
|
|
|
|
- name: ccache-clear
|
|
uses: ./.github/actions/ccache-clear
|
|
env:
|
|
GH_TOKEN: ${{ github.token }}
|
|
with:
|
|
key: webgpu-ubuntu-24.04
|
|
older: 5m
|
|
min: 1
|
|
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
|