Georgi Gerganov
6b9ba4f2e8
* ci : fix data race between runners sharing the model cache Two runners per mac mini share HOME, so concurrent jobs corrupt each other downloads, converted models and venv under the shared MNT cache. - gg_wget: download in a temp dir, publish with mv, so readers only ever see complete files (-N cannot be combined with -O) - convert, quantize and wikitext unzip now produce under a per-runner scratch dir in OUT, published to MNT via hardlink when missing - gguf-split and quantize tests get a per-runner TMP_DIR - python venv moved from MNT to OUT - metal, vulkan and webgpu mac jobs pass a per-runner OUT path Assisted-by: dsh:llama.cpp/agent-qwen4 (RTX 5090 machine) * ci : clean up scratch models after tests Assisted-by: dsh:llama.cpp/agent-qwen4 (RTX 5090 machine) * ci : fix q4_0 publish when a cached model exists cp -n skips an existing file with exit code 1, so the ln fallback aborted the qwen3 job under set -e. Publish through a unique temp file with an atomic mv: readers never see a partial file and a stale cached q4_0 gets replaced. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (RTX 5090 machine) * ci : cache-first gg_wget to avoid re-downloads HF sends no Last-Modified, so wget -N re-downloads the full files on every run. Skip the download when a non-empty cache file exists: the HF CI artifacts are static. Downloads still go through a temp dir and an atomic mv, so concurrent runners never read partial files. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (RTX 5090 machine)
135 lines
4.1 KiB
YAML
135 lines
4.1 KiB
YAML
name: CI (self-hosted WebGPU backend)
|
|
|
|
on:
|
|
workflow_dispatch: # allows manual triggering
|
|
push:
|
|
branches:
|
|
- master
|
|
paths: [
|
|
'.github/workflows/ci-self-hosted-webgpu.yml',
|
|
'ci/run.sh',
|
|
'**/CMakeLists.txt',
|
|
'**/.cmake',
|
|
'**/*.h',
|
|
'**/*.hpp',
|
|
'**/*.c',
|
|
'**/*.cpp',
|
|
'**/*.wgsl'
|
|
]
|
|
|
|
pull_request:
|
|
types: [opened, synchronize, reopened]
|
|
paths: [
|
|
'.github/workflows/ci-self-hosted-webgpu.yml',
|
|
'ci/run.sh',
|
|
'**/CMakeLists.txt',
|
|
'**/.cmake',
|
|
'ggml/src/*',
|
|
'ggml/src/ggml-cpu/**',
|
|
'ggml/src/ggml-webgpu/**'
|
|
]
|
|
|
|
cache-mode: none
|
|
permissions:
|
|
contents: read
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
|
|
cancel-in-progress: true
|
|
|
|
env:
|
|
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
|
|
GGML_NLOOP: 3
|
|
GGML_N_THREADS: 1
|
|
LLAMA_ARG_LOG_COLORS: 1
|
|
LLAMA_ARG_LOG_PREFIX: 1
|
|
LLAMA_ARG_LOG_TIMESTAMPS: 1
|
|
|
|
jobs:
|
|
gpu-webgpu-nvidia:
|
|
runs-on: "hf-jobs-t4-small:ubuntu26_04"
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
sudo apt update
|
|
sudo apt install -y build-essential cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan1 mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 libssl-dev time unzip wget python3 python3-venv python3-pip
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.24
|
|
with:
|
|
restore: false
|
|
save: false
|
|
|
|
- name: ccache-buckets-restore
|
|
uses: ./.github/actions/ccache-buckets
|
|
with:
|
|
key: self-hosted-webgpu-nvidia
|
|
folder: llama.cpp
|
|
hf_bucket: ggml-org/cache
|
|
|
|
- name: Dawn Dependency
|
|
id: dawn-depends
|
|
run: |
|
|
DAWN_VERSION="v20260908.214631"
|
|
DAWN_OWNER="google"
|
|
DAWN_REPO="dawn"
|
|
DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-ubuntu-latest-Release"
|
|
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
|
|
curl -L -o artifact.tar.gz \
|
|
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
|
|
mkdir dawn
|
|
tar -xvf artifact.tar.gz -C dawn --strip-components=1
|
|
|
|
- name: Test
|
|
id: ggml-ci
|
|
run: |
|
|
GG_BUILD_WEBGPU=1 \
|
|
GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
|
|
GG_BUILD_WEBGPU_DAWN_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \
|
|
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
|
|
|
|
- name: ccache-buckets-save
|
|
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
uses: ./.github/actions/ccache-buckets
|
|
env:
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
|
|
with:
|
|
key: self-hosted-webgpu-nvidia
|
|
folder: llama.cpp
|
|
evict-old-files: 1d
|
|
hf_bucket: ggml-org/cache
|
|
save: true
|
|
|
|
gpu-webgpu-apple:
|
|
runs-on: [self-hosted, macOS, ARM64]
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Dawn Dependency
|
|
id: dawn-depends
|
|
run: |
|
|
DAWN_VERSION="v20260908.214631"
|
|
DAWN_OWNER="google"
|
|
DAWN_REPO="dawn"
|
|
DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-macos-latest-Release"
|
|
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${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/$RUNNER_NAME ~/mnt/llama.cpp
|