minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[NPU]Add a full test pipeline on NPU, resolve issues in the NPU test architecture (#20751)

Browse Source
This commit is contained in:
Cherry_ming
2026-04-01 19:56:31 +08:00
committed by GitHub
parent ac039bd04e
commit e67b95d66b
43 changed files with 673 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/full-test-npu.yml
+355
View File
@@ -0,0 +1,355 @@
name: Full Test (NPU)
on:
# pull_request:
# branches:
# - main
# paths:
# - ".github/workflows/full-test-npu.yml"
workflow_dispatch:
inputs:
ref:
description: 'Git ref (branch, tag, or SHA) to test. If not provided, uses the default branch.'
required: false
type: string
default: ''
job_filter:
description: 'Select which job to run (leave empty or "all" to run all jobs)'
required: false
type: string
default: 'all'
image_a3:
description: 'The a3 running docker image of the test task.'
required: false
type: string
default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11'
skip_install_flag:
description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
required: false
type: string
default: 'false'
concurrency:
group: full-test-npu-${{ inputs.ref || github.ref }}
cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
jobs:
set-image-config:
runs-on: ubuntu-latest
outputs:
ref: ${{ steps.set-vars.outputs.ref }}
job_filter: ${{ steps.set-vars.outputs.job_filter }}
image_a3: ${{ steps.set-vars.outputs.image_a3 }}
skip_install_flag: ${{ steps.set-vars.outputs.skip_install_flag }}
steps:
# When triggered by PR, no inputs parameters are used. The latest community code is tested by default.
- name: Set image config
id: set-vars
run: |
if [ -z "${{ inputs.ref }}" ]; then
echo "ref=" >> $GITHUB_OUTPUT
else
echo "ref=${{ inputs.ref }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.job_filter }}" ]; then
echo "job_filter=all" >> $GITHUB_OUTPUT
else
echo "job_filter=${{ inputs.job_filter }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.image_a3 }}" ]; then
echo "image_a3=swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11" >> $GITHUB_OUTPUT
else
echo "image_a3=${{ inputs.image_a3 }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.skip_install_flag }}" ]; then
echo "skip_install_flag=false" >> $GITHUB_OUTPUT
else
echo "skip_install_flag=${{ inputs.skip_install_flag }}" >> $GITHUB_OUTPUT
fi
nighly-test-npu:
needs: [set-image-config]
name: nightly-test-npu
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
uses: ./.github/workflows/nightly-test-npu.yml
with:
ref: ${{ needs.set-image-config.outputs.ref }}
job_filter: ${{ needs.set-image-config.outputs.job_filter }}
image_a3: ${{ needs.set-image-config.outputs.image_a3 }}
skip_install_flag: ${{ needs.set-image-config.outputs.skip_install_flag }}
secrets: inherit
full-1-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-2
container:
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
bash scripts/ci/npu/npu_log_print.sh
- name: Run test
timeout-minutes: 240
env:
SGLANG_USE_MODELSCOPE: true
SGLANG_IS_IN_CI: true
HF_ENDPOINT: https://hf-mirror.com
TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
cd ./lmms-eval
nohup pip install . > lmmslog.txt 2>&1 &
sleep 120
export PYTHONPATH=$PYTHONPATH:$(pwd)
cd ../
cd test
python3 run_suite.py --hw npu --suite full-1-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
full-2-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-2
container:
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
bash scripts/ci/npu/npu_log_print.sh
- name: Run test
timeout-minutes: 240
env:
SGLANG_USE_MODELSCOPE: true
SGLANG_IS_IN_CI: true
HF_ENDPOINT: https://hf-mirror.com
TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
cd ./lmms-eval
nohup pip install . > lmmslog.txt 2>&1 &
sleep 120
export PYTHONPATH=$PYTHONPATH:$(pwd)
cd ../
cd test
python3 run_suite.py --hw npu --suite full-2-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
full-4-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-4
container:
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
bash scripts/ci/npu/npu_log_print.sh
- name: Run test
timeout-minutes: 240
env:
SGLANG_USE_MODELSCOPE: true
SGLANG_IS_IN_CI: true
HF_ENDPOINT: https://hf-mirror.com
TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
cd ./lmms-eval
nohup pip install . > lmmslog.txt 2>&1 &
sleep 120
export PYTHONPATH=$PYTHONPATH:$(pwd)
cd ../
cd test
python3 run_suite.py --hw npu --suite full-4-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
full-16-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-16
container:
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
bash scripts/ci/npu/npu_log_print.sh
- name: Run test
timeout-minutes: 240
env:
SGLANG_USE_MODELSCOPE: true
SGLANG_IS_IN_CI: true
HF_ENDPOINT: https://hf-mirror.com
TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install protobuf==6.31.1 zss pre-commit wandb>=0.16.0 tenacity==8.3.0 loguru openpyxl latex2sympy2 zstandard transformers-stream-generator tqdm-multiprocess pycocoevalcap
pip install yt-dlp sentencepiece==0.1.99 nltk av ftfy sqlitedict==2.1.0 sacrebleu>=1.5.0 pytablewriter black==24.1.0 isort==5.13.2 peft>=0.2.0 accelerate>=0.29.1
pip install jsonlines httpx==0.25.0 evaluate>=0.4.0 datasets==2.16.1 numexpr xgrammar==0.1.25 numpy==1.26.4 dotenv
git clone --branch v0.3.3 --depth 1 https://github.com/EvolvingLMMs-Lab/lmms-eval.git
cd ./lmms-eval
nohup pip install . > lmmslog.txt 2>&1 &
sleep 120
export PYTHONPATH=$PYTHONPATH:$(pwd)
cd ../
cd test
python3 run_suite.py --hw npu --suite full-16-npu-a3 --nightly --continue-on-error --timeout-per-file 3600
check-all-jobs:
if: github.repository == 'sgl-project/sglang' && always()
needs:
- nighly-test-npu
- full-1-npu-a3
- full-2-npu-a3
- full-4-npu-a3
- full-16-npu-a3
runs-on: ubuntu-latest
container:
image: docker.m.daocloud.io/ubuntu:22.04
steps:
- name: Check if any job failed
run: |
if [[ "${{ contains(needs.*.result, 'failure') }}" == "true" ]]; then
echo "One or more nightly test jobs failed"
exit 1
fi
if [[ "${{ contains(needs.*.result, 'cancelled') }}" == "true" ]]; then
echo "One or more nightly test jobs were cancelled"
exit 1
fi
echo "All nightly test jobs passed"
.github/workflows/nightly-test-npu.yml
+124 -36
View File
@@ -2,7 +2,7 @@ name: Nightly Test (NPU)
on:
schedule:
- cron: '0 17 * * *' # Execute at 1:00 a.m. Beijing Time every day
- cron: '0 18 * * *' # Execute at 2:00 a.m. Beijing Time every day
pull_request:
branches:
- main
@@ -21,13 +21,61 @@ on:
required: false
type: string
default: 'all'
image_a3:
description: 'The a3 running docker image of the test task.'
required: false
type: string
default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11'
skip_install_flag:
description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
required: false
type: string
default: 'false'
concurrency:
group: nightly-test-npu-${{ inputs.ref || github.ref }}
cancel-in-progress: ${{ github.event_name != 'workflow_call' }}
jobs:
set-image-config:
runs-on: ubuntu-latest
outputs:
ref: ${{ steps.set-vars.outputs.ref }}
job_filter: ${{ steps.set-vars.outputs.job_filter }}
image_a3: ${{ steps.set-vars.outputs.image_a3 }}
skip_install_flag: ${{ steps.set-vars.outputs.skip_install_flag }}
steps:
# When triggered by PR, no inputs parameters are used. The latest community code is tested by default.
- name: Set image config
id: set-vars
run: |
if [ -z "${{ inputs.ref }}" ]; then
echo "ref=" >> $GITHUB_OUTPUT
else
echo "ref=${{ inputs.ref }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.job_filter }}" ]; then
echo "job_filter=all" >> $GITHUB_OUTPUT
else
echo "job_filter=${{ inputs.job_filter }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.image_a3 }}" ]; then
echo "image_a3=swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11" >> $GITHUB_OUTPUT
else
echo "image_a3=${{ inputs.image_a3 }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.skip_install_flag }}" ]; then
echo "skip_install_flag=false" >> $GITHUB_OUTPUT
else
echo "skip_install_flag=${{ inputs.skip_install_flag }}" >> $GITHUB_OUTPUT
fi
nightly-1-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-2
strategy:
@@ -35,26 +83,33 @@ jobs:
matrix:
part: [0, 1]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
@@ -86,6 +141,7 @@ jobs:
python3 run_suite.py --hw npu --suite nightly-1-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
nightly-2-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-2
strategy:
@@ -93,26 +149,33 @@ jobs:
matrix:
part: [0]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
@@ -143,6 +206,7 @@ jobs:
python3 run_suite.py --hw npu --suite nightly-2-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
nightly-4-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-4
strategy:
@@ -150,25 +214,33 @@ jobs:
matrix:
part: [0]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
ref: ${{ needs.set-image-config.outputs.ref|| github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
@@ -200,6 +272,7 @@ jobs:
python3 run_suite.py --hw npu --suite nightly-4-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
nightly-8-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-8
strategy:
@@ -207,26 +280,33 @@ jobs:
matrix:
part: [0]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
@@ -258,6 +338,7 @@ jobs:
python3 run_suite.py --hw npu --suite nightly-8-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
nightly-16-npu-a3:
needs: [set-image-config]
if: ${{ (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') }}
runs-on: linux-aarch64-a3-16
strategy:
@@ -265,26 +346,33 @@ jobs:
matrix:
part: [0, 1]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
ref: ${{ needs.set-image-config.outputs.ref || github.ref }}
- name: Install dependencies
env:
TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
run: |
# speed up by using infra cache services
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
pip config set global.trusted-host "${CACHING_URL}"
if [ ${{ needs.set-image-config.outputs.skip_install_flag }} != "true" ];then
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
fi
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Print Log Information
run: |
.github/workflows/pr-test-npu.yml
+70 -40
View File
@@ -76,7 +76,7 @@ jobs:
uses: ./.github/workflows/pr-gate.yml
secrets: inherit
per-commit-1-npu-a2:
stage-b-test-1-npu-a2:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-1
@@ -111,21 +111,8 @@ jobs:
bash scripts/ci/npu/npu_ci_install_dependency.sh 910b
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
- name: Run registered test
timeout-minutes: 240
env:
SGLANG_USE_MODELSCOPE: true
SGLANG_IS_IN_CI: true
HF_ENDPOINT: https://hf-mirror.com
TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
cd test
python3 run_suite.py --hw npu --suite per-commit-1-npu-a2 --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Run test
timeout-minutes: 60
@@ -137,10 +124,10 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
cd test/srt
python3 run_suite.py --suite per-commit-1-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
cd test
python3 run_suite.py --hw npu --suite stage-b-test-1-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
per-commit-2-npu-a2:
stage-b-test-2-npu-a2:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-2
@@ -175,8 +162,8 @@ jobs:
bash scripts/ci/npu/npu_ci_install_dependency.sh 910b
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Run test
timeout-minutes: 60
@@ -188,10 +175,10 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
cd test/srt
python3 run_suite.py --suite per-commit-2-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
cd test
python3 run_suite.py --hw npu --suite stage-b-test-2-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
per-commit-4-npu-a3:
stage-b-test-4-npu-a3:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a3-4
@@ -222,8 +209,8 @@ jobs:
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Run test
timeout-minutes: 60
@@ -235,10 +222,11 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
cd test/srt
python3 run_suite.py --suite per-commit-4-npu-a3 --timeout-per-file 3600
cd test
python3 run_suite.py --hw npu --suite stage-b-test-4-npu-a3 --timeout-per-file 3600
per-commit-16-npu-a3:
stage-b-test-16-npu-a3:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a3-16
@@ -269,8 +257,8 @@ jobs:
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Run test
timeout-minutes: 60
@@ -282,8 +270,8 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
cd test/srt
python3 run_suite.py --suite per-commit-16-npu-a3 --timeout-per-file 3600
cd test
python3 run_suite.py --hw npu --suite stage-b-test-16-npu-a3 --timeout-per-file 3600
multimodal-gen-test-1-npu-a3:
needs: [check-changes, pr-gate]
@@ -314,8 +302,8 @@ jobs:
bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Run test
timeout-minutes: 60
@@ -360,8 +348,8 @@ jobs:
bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Run test
timeout-minutes: 60
@@ -380,7 +368,7 @@ jobs:
multimodal-gen-test-8-npu-a3:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.multimodal_gen == 'true'
runs-on: linux-aarch64-a3-16
runs-on: linux-aarch64-a3-8
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
steps:
@@ -406,8 +394,8 @@ jobs:
bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl
# copy gsm8k dataset
cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
- name: Run test
timeout-minutes: 60
@@ -421,3 +409,45 @@ jobs:
run: |
cd python
python3 sglang/multimodal_gen/test/run_suite.py --suite 8-npu
pr-test-finish:
needs:
[
check-changes,
stage-b-test-1-npu-a2,
stage-b-test-2-npu-a2,
stage-b-test-4-npu-a3,
stage-b-test-16-npu-a3,
multimodal-gen-test-1-npu-a3,
multimodal-gen-test-2-npu-a3,
multimodal-gen-test-8-npu-a3,
]
if: always()
runs-on: ubuntu-latest
steps:
- name: Check all dependent job statuses
run: |
# Convert the 'needs' context to a JSON string
json_needs='${{ toJson(needs) }}'
# Get a list of all job names from the JSON keys
job_names=$(echo "$json_needs" | jq -r 'keys_unsorted[]')
for job in $job_names; do
# For each job, extract its result
result=$(echo "$json_needs" | jq -r --arg j "$job" '.[$j].result')
# Print the job name and its result
echo "$job: $result"
# Check for failure or cancellation and exit if found
if [[ "$result" == "failure" || "$result" == "cancelled" ]]; then
echo "The above jobs failed."
exit 1
fi
done
# If the loop completes, all jobs were successful
echo "All jobs completed successfully"
exit 0
.github/workflows/release-docker-npu-nightly.yml
+1 -1
View File
@@ -8,7 +8,7 @@ on:
- 'docker/npu.Dockerfile'
workflow_dispatch:
schedule:
- cron: "0 0 * * *"
- cron: "0 16 * * *" # Execute at 0:00 a.m. Beijing Time every day
concurrency:
group: ${{ github.workflow }}-${{ github.sha }}