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

[NPU] chore: basic software upgrade (#26466)

Browse Source
This commit is contained in:
monkeyLoveding
2026-05-29 10:04:15 +08:00
committed by GitHub
parent 54b06f199c
commit 7619e77b7b
6 changed files with 75 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/nightly-test-npu.yml
+6 -6
View File
@@ -63,7 +63,7 @@ jobs:
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
echo "image_a3=swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:9.0.0-a3-ubuntu22.04-py3.11" >> $GITHUB_OUTPUT
else
echo "image_a3=${{ inputs.image_a3 }}" >> $GITHUB_OUTPUT
fi
@@ -128,7 +128,7 @@ jobs:
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install sentence_transformers torchaudio==2.10.0
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==0.2.0 numpy==1.26.4 dotenv
@@ -194,7 +194,7 @@ jobs:
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install sentence_transformers torchaudio==2.10.0
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==0.2.0 numpy==1.26.4 dotenv
@@ -261,7 +261,7 @@ jobs:
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install sentence_transformers torchaudio==2.10.0
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==0.2.0 numpy==1.26.4 dotenv
@@ -328,7 +328,7 @@ jobs:
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install sentence_transformers torchaudio==2.10.0
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==0.2.0 numpy==1.26.4 dotenv
@@ -395,7 +395,7 @@ jobs:
run: |
pip install sglang_router
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0
pip install sentence_transformers torchaudio==2.10.0
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==0.2.0 numpy==1.26.4 dotenv
.github/workflows/pr-test-npu.yml
+30 -19
View File
@@ -77,8 +77,21 @@ jobs:
uses: ./.github/workflows/pr-gate.yml
secrets: inherit
set-image-config:
runs-on: ubuntu-latest
outputs:
CANN_image_a3: ${{ steps.set-vars.outputs.CANN_image_a3 }}
CANN_image_910b: ${{ steps.set-vars.outputs.CANN_image_910b }}
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: |
echo "CANN_image_a3=swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:9.0.0-a3-ubuntu22.04-py3.11" >> $GITHUB_OUTPUT
echo "CANN_image_910b=swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:9.0.0-910b-ubuntu22.04-py3.11" >> $GITHUB_OUTPUT
stage-b-test-1-npu-a2:
needs: [check-changes, pr-gate]
needs: [check-changes, pr-gate, set-image-config]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-1
strategy:
@@ -86,7 +99,7 @@ jobs:
matrix:
part: [ 0, 1 ]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.CANN_image_910b }}
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -131,7 +144,7 @@ jobs:
python3 run_suite.py --hw npu --suite stage-b-test-1-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
stage-b-test-2-npu-a2:
needs: [check-changes, pr-gate]
needs: [check-changes, pr-gate, set-image-config]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-2
strategy:
@@ -139,7 +152,7 @@ jobs:
matrix:
part: [0, 1]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
image: $${{ needs.set-image-config.outputs.CANN_image_910b }}
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -184,11 +197,11 @@ jobs:
python3 run_suite.py --hw npu --suite stage-b-test-2-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
stage-b-test-4-npu-a3:
needs: [check-changes, pr-gate]
needs: [check-changes, pr-gate, set-image-config]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a3-4
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.CANN_image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -234,11 +247,11 @@ jobs:
stage-b-test-16-npu-a3:
needs: [check-changes, pr-gate]
needs: [check-changes, pr-gate, set-image-config]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a3-16
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.CANN_image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -283,11 +296,11 @@ jobs:
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]
needs: [check-changes, pr-gate, set-image-config]
if: needs.check-changes.outputs.multimodal_gen == 'true'
runs-on: linux-aarch64-a3-2
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.CANN_image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -310,7 +323,7 @@ jobs:
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
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 gsm8k dataset
@@ -327,7 +340,6 @@ jobs:
STREAMS_PER_DEVICE: 32
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
cd python
python3 sglang/multimodal_gen/test/run_suite_npu.py --suite 1-npu
@@ -341,11 +353,11 @@ jobs:
retention-days: 7
multimodal-gen-test-2-npu-a3:
needs: [check-changes, pr-gate]
needs: [check-changes, pr-gate, set-image-config]
if: needs.check-changes.outputs.multimodal_gen == 'true'
runs-on: linux-aarch64-a3-16
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
image: ${{ needs.set-image-config.outputs.CANN_image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -368,7 +380,7 @@ jobs:
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
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 gsm8k dataset
@@ -385,7 +397,6 @@ jobs:
STREAMS_PER_DEVICE: 32
SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
cd python
python3 sglang/multimodal_gen/test/run_suite_npu.py --suite 2-npu
@@ -399,11 +410,11 @@ jobs:
retention-days: 7
multimodal-gen-test-8-npu-a3:
needs: [check-changes, pr-gate]
needs: [check-changes, pr-gate, set-image-config]
if: needs.check-changes.outputs.multimodal_gen == 'true'
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
image: ${{ needs.set-image-config.outputs.CANN_image_a3 }}
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -426,7 +437,7 @@ jobs:
pip config set global.index-url http://${CACHING_URL}/pypi/simple
pip config set global.trusted-host "${CACHING_URL}"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3 diffusion
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 gsm8k dataset
.github/workflows/release-docker-npu-nightly.yml
+2 -2
View File
@@ -19,7 +19,7 @@ jobs:
runs-on: ubuntu-22.04-arm
strategy:
matrix:
cann_version: ["8.5.0"]
cann_version: ["9.0.0"]
device_type: ["910b", "a3"]
steps:
- name: Checkout repository
@@ -80,6 +80,6 @@ jobs:
push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
provenance: false
build-args: |
SGLANG_KERNEL_NPU_TAG=2026.05.01
SGLANG_KERNEL_NPU_TAG=2026.05.01.post3
CANN_VERSION=${{ matrix.cann_version }}
DEVICE_TYPE=${{ matrix.device_type }}
.github/workflows/release-docker-npu.yml
+2 -2
View File
@@ -14,7 +14,7 @@ jobs:
runs-on: ubuntu-22.04-arm
strategy:
matrix:
cann_version: ["8.5.0"]
cann_version: ["9.0.0"]
device_type: ["910b", "a3"]
steps:
- name: Checkout repository
@@ -87,7 +87,7 @@ jobs:
push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
provenance: false
build-args: |
SGLANG_KERNEL_NPU_TAG=2026.05.01
SGLANG_KERNEL_NPU_TAG=2026.05.01.post3
CANN_VERSION=${{ matrix.cann_version }}
DEVICE_TYPE=${{ matrix.device_type }}
SGLANG_TAG=${{ steps.version.outputs.version }}