ggml-webgpu: Enable NVIDIA self-hosted CI (#22976)

* Enabel nvidia ci for webgpu

* Address precision issues

* fix placement

* Relax more set_rows and div

* Try relaxing all f16

* formatting and naming

* Add comment explaining max_nmse_err logic

Added comment referencing pull request for clarification.
This commit is contained in:
Reese Levine
2026-05-14 09:41:32 -07:00
committed by GitHub
parent 5ec717d125
commit 834a243664
2 changed files with 54 additions and 28 deletions
+25 -26
View File
@@ -120,35 +120,34 @@ jobs:
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
# TODO: investigate slight precision issues in some operations for test-backend-ops on the WebGPU backend.
#ggml-ci-nvidia-webgpu:
# runs-on: [self-hosted, Linux, NVIDIA]
ggml-ci-nvidia-webgpu:
runs-on: [self-hosted, Linux, NVIDIA]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
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-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: Dawn Dependency
id: dawn-depends
run: |
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: 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: 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
# TODO: provision AMX-compatible machine
#ggml-ci-cpu-amx: