Files
llama.cpp/.github/workflows/ci-self-hosted-openvino.yml
T

76 lines
2.1 KiB
YAML

name: CI (self-hosted OpenVINO backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-openvino.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-openvino.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**',
'ggml/src/ggml-openvino/**'
]
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-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: "2026.4"
OPENVINO_VERSION_FULL: "2026.4.0.22959.99c81491cc3"
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