openvino: driver setup, CI split, thread safety, and NPU optimizations (#21944)
* Thread safety per request only * Fix ROPE yarn case * Fix sticky stateful config * Use i4/i8 directly for symmetric quant * Use weightless caching * Add WeightlessCacheAttribute to reduce NPU memory usage * Gelu tanh support (#125) * Imrope support (#126) * fix(openvino): explicit ov::Tensor frees in ggml_backend_openvino_free * add GPU,NPU support in OV Dockerfile * add build-openvino.yml ci * Fix sticky stateful config * add concurrency to ov-gpu ci runs. Move OV CI to build-openvino.yml * fix thread-safety of shared runtime context * rope type abstraction for frontend translations * fix editorconfig --------- Co-authored-by: Mustafa Cavus <mustafa.cavus@intel.com> Co-authored-by: Dan Hoffman <dhoff749@gmail.com> Co-authored-by: Ravi Panchumarthy <ravi.panchumarthy@intel.com>
This commit is contained in:
Zijun Yu
@@ -0,0 +1,120 @@
|
||||
name: CI (openvino)
|
||||
|
||||
on:
|
||||
workflow_dispatch: # allows manual triggering
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
paths: [
|
||||
'.github/workflows/build-openvino.yml',
|
||||
'**/CMakeLists.txt',
|
||||
'**/.cmake',
|
||||
'**/*.h',
|
||||
'**/*.hpp',
|
||||
'**/*.c',
|
||||
'**/*.cpp',
|
||||
]
|
||||
|
||||
pull_request:
|
||||
types: [opened, synchronize, reopened]
|
||||
paths: [
|
||||
'.github/workflows/build-openvino.yml',
|
||||
'ggml/src/ggml-openvino/**'
|
||||
]
|
||||
|
||||
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_LOG_COLORS: 1
|
||||
LLAMA_LOG_PREFIX: 1
|
||||
LLAMA_LOG_TIMESTAMPS: 1
|
||||
|
||||
jobs:
|
||||
ubuntu-24-openvino:
|
||||
name: ubuntu-24-openvino-${{ matrix.openvino_device }}
|
||||
|
||||
concurrency:
|
||||
group: openvino-${{ matrix.variant }}-${{ github.head_ref || github.ref }}
|
||||
cancel-in-progress: false
|
||||
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- variant: cpu
|
||||
runner: '"ubuntu-24.04"'
|
||||
openvino_device: "CPU"
|
||||
- variant: gpu
|
||||
runner: '["self-hosted","Linux","Intel","OpenVINO"]'
|
||||
openvino_device: "GPU"
|
||||
|
||||
runs-on: ${{ fromJSON(matrix.runner) }}
|
||||
|
||||
env:
|
||||
# Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
|
||||
OPENVINO_VERSION_MAJOR: "2026.0"
|
||||
OPENVINO_VERSION_FULL: "2026.0.0.20965.c6d6a13a886"
|
||||
|
||||
steps:
|
||||
- name: Clone
|
||||
id: checkout
|
||||
uses: actions/checkout@v6
|
||||
|
||||
- name: ccache
|
||||
if: runner.environment == 'github-hosted'
|
||||
uses: ggml-org/ccache-action@v1.2.21
|
||||
with:
|
||||
key: ubuntu-24-openvino-${{ matrix.variant }}-no-preset-v1
|
||||
evict-old-files: 1d
|
||||
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
||||
|
||||
- name: Dependencies
|
||||
id: depends
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y build-essential libssl-dev libtbb12 cmake ninja-build python3-pip
|
||||
sudo apt-get install -y ocl-icd-opencl-dev opencl-headers opencl-clhpp-headers intel-opencl-icd
|
||||
|
||||
- name: Use OpenVINO Toolkit Cache
|
||||
if: runner.environment == 'github-hosted'
|
||||
uses: actions/cache@v5
|
||||
id: cache-openvino
|
||||
with:
|
||||
path: ./openvino_toolkit
|
||||
key: openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
|
||||
|
||||
- name: Setup OpenVINO Toolkit
|
||||
if: steps.cache-openvino.outputs.cache-hit != 'true'
|
||||
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: Build
|
||||
id: cmake_build
|
||||
run: |
|
||||
source ./openvino_toolkit/setupvars.sh
|
||||
cmake -B build/ReleaseOV -G Ninja \
|
||||
-DCMAKE_BUILD_TYPE=Release \
|
||||
-DGGML_OPENVINO=ON
|
||||
time cmake --build build/ReleaseOV --config Release -j $(nproc)
|
||||
|
||||
- name: Test
|
||||
id: cmake_test
|
||||
# TODO: fix and re-enable the `test-llama-archs` test below
|
||||
run: |
|
||||
cd ${{ github.workspace }}
|
||||
if [ "${{ matrix.openvino_device }}" = "GPU" ]; then
|
||||
export GGML_OPENVINO_DEVICE=GPU
|
||||
fi
|
||||
ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 2000
|
||||
@@ -265,6 +265,10 @@ jobs:
|
||||
ggml-ci-intel-openvino-gpu-low-perf:
|
||||
runs-on: [self-hosted, Linux, Intel, OpenVINO]
|
||||
|
||||
concurrency:
|
||||
group: openvino-gpu-${{ github.head_ref || github.ref }}
|
||||
cancel-in-progress: false
|
||||
|
||||
env:
|
||||
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
|
||||
OPENVINO_VERSION_MAJOR: "2026.0"
|
||||
|
||||
@@ -656,86 +656,6 @@ jobs:
|
||||
-DGGML_SYCL_F16=ON
|
||||
time cmake --build build --config Release -j $(nproc)
|
||||
|
||||
ubuntu-24-openvino:
|
||||
name: ubuntu-24-openvino-${{ matrix.openvino_device }}
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- variant: cpu
|
||||
runner: '"ubuntu-24.04"'
|
||||
openvino_device: "CPU"
|
||||
- variant: gpu
|
||||
runner: '["self-hosted","Linux","X64","Intel"]'
|
||||
openvino_device: "GPU"
|
||||
|
||||
runs-on: ${{ fromJSON(matrix.runner) }}
|
||||
|
||||
env:
|
||||
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
|
||||
OPENVINO_VERSION_MAJOR: "2026.0"
|
||||
OPENVINO_VERSION_FULL: "2026.0.0.20965.c6d6a13a886"
|
||||
|
||||
steps:
|
||||
- name: Clone
|
||||
id: checkout
|
||||
uses: actions/checkout@v6
|
||||
|
||||
- name: ccache
|
||||
if: runner.environment == 'github-hosted'
|
||||
uses: ggml-org/ccache-action@v1.2.21
|
||||
with:
|
||||
key: ubuntu-24-openvino-${{ matrix.variant }}-no-preset-v1
|
||||
evict-old-files: 1d
|
||||
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
||||
|
||||
- name: Dependencies
|
||||
id: depends
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y build-essential libssl-dev libtbb12 cmake ninja-build python3-pip
|
||||
sudo apt-get install -y ocl-icd-opencl-dev opencl-headers opencl-clhpp-headers intel-opencl-icd
|
||||
|
||||
- name: Use OpenVINO Toolkit Cache
|
||||
if: runner.environment == 'github-hosted'
|
||||
uses: actions/cache@v5
|
||||
id: cache-openvino
|
||||
with:
|
||||
path: ./openvino_toolkit
|
||||
key: openvino-toolkit-v${{ env.OPENVINO_VERSION_FULL }}-${{ runner.os }}
|
||||
|
||||
- name: Setup OpenVINO Toolkit
|
||||
if: steps.cache-openvino.outputs.cache-hit != 'true'
|
||||
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: Build
|
||||
id: cmake_build
|
||||
run: |
|
||||
source ./openvino_toolkit/setupvars.sh
|
||||
cmake -B build/ReleaseOV -G Ninja \
|
||||
-DCMAKE_BUILD_TYPE=Release \
|
||||
-DGGML_OPENVINO=ON
|
||||
time cmake --build build/ReleaseOV --config Release -j $(nproc)
|
||||
|
||||
- name: Test
|
||||
id: cmake_test
|
||||
# TODO: fix and re-enable the `test-llama-archs` test below
|
||||
run: |
|
||||
cd ${{ github.workspace }}
|
||||
if [ "${{ matrix.openvino_device }}" = "GPU" ]; then
|
||||
export GGML_OPENVINO_DEVICE=GPU
|
||||
fi
|
||||
ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 2000
|
||||
|
||||
windows-latest:
|
||||
runs-on: windows-2025
|
||||
|
||||
|
||||
Reference in New Issue
Block a user