Skip to content

ci: try using gpu-webgpu-intel in CI #26258

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
yomaytk wants to merge 1 commit into
base: master
Choose a base branch
from
+4 −324
Draft

ci: try using gpu-webgpu-intel in CI #26258

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
328 changes: 4 additions & 324 deletions .github/workflows/build-self-hosted.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,75 +57,15 @@ env:
LLAMA_ARG_LOG_TIMESTAMPS: 1

jobs:
gpu-cuda:
runs-on: [self-hosted, Linux, NVIDIA]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
run: |
nvidia-smi
GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-rocm:
runs-on: [self-hosted, Linux, AMD]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
# HIP_LAUNCH_BLOCKING=1: workaround for an async-execution correctness
# issue on integrated RDNA3.5 (gfx1151) where batched inference returns
# incorrect output (perplexity ~88 vs ~9.4). Serializing kernel launches
# restores correctness. Remove once the underlying ROCm/HIP issue is fixed.
env:
HIP_LAUNCH_BLOCKING: "1"
run: |
rocminfo
GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS=gfx1151 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-vulkan-nvidia-cm:
runs-on: [self-hosted, Linux, NVIDIA]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-vulkan-nvidia-cm2:
runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-webgpu-nvidia:
runs-on: [self-hosted, Linux, NVIDIA, X64]
gpu-webgpu-intel:
runs-on: [self-hosted, Linux, Intel, X64]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
persist-credentials: false

- name: Dawn Dependency
id: dawn-depends
Expand All @@ -147,263 +87,3 @@ jobs:
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

# TODO: provision AMX-compatible machine
#cpu-amx:
# runs-on: [self-hosted, Linux, CPU, AMX]

# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6

# - name: Test
# id: ggml-ci
# run: |
# bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

# TODO: provision AMD GPU machine
# amd-vulkan:
# runs-on: [self-hosted, Linux, AMD]

# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6

# - name: Test
# id: ggml-ci
# run: |
# vulkaninfo --summary
# GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

# TODO: provision AMD GPU machine
# amd-rocm:
# runs-on: [self-hosted, Linux, AMD]

# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6

# - name: Test
# id: ggml-ci
# run: |
# amd-smi static
# GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-metal:
runs-on: [self-hosted, macOS, ARM64]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
run: |
GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

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="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: Test
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-vulkan-apple:
runs-on: [self-hosted, macOS, ARM64]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-vulkan-intel-linux:
runs-on: [self-hosted, Linux, Intel]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
persist-credentials: false

- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

gpu-vulkan-intel-windows:
runs-on: [self-hosted, Windows, X64, Intel]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
shell: C:\msys64\usr\bin\bash.exe --noprofile --norc -eo pipefail "{0}"
env:
MSYSTEM: UCRT64
CHERE_INVOKING: 1
PATH: C:\msys64\ucrt64\bin;C:\msys64\usr\bin;C:\Windows\System32;${{ env.PATH }}
run: |
vulkaninfo --summary
# Skip python related tests with GG_BUILD_LOW_PERF=1 since Windows MSYS2 UCRT64 currently fails to create
# a valid python environment for testing
LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp

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: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"

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

cpu-x64-high-perf:
runs-on: [self-hosted, Linux, X64]

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

cpu-arm64-high-perf-graviton4:
runs-on: ah-ubuntu_22_04-c8g_8x

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs

git lfs install

# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake

- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

cpu-arm64-graviton4-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x

steps:
- name: Clone
id: checkout
uses: actions/checkout@v6

- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs

git lfs install

# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake

- name: Test
id: ggml-ci
run: |
GG_BUILD_KLEIDIAI=1 \
GG_BUILD_EXTRA_TESTS_0=1 \
bash ./ci/run.sh ./tmp/results ./tmp/mnt
Loading