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

[NPU] Adapt cann 8.5: use sfa and lightning indexer op from cann and CI update (#17615)

Browse Source 
Co-authored-by: Kelon <kelonlu@163.com>
This commit is contained in:
monkeyLoveding
2026-01-27 19:03:53 +08:00
committed by GitHub
co-authored by Kelon
parent 832c756549
commit d578b41bad
9 changed files with 52 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/nightly-test-npu.yml
+4 -8
View File
@@ -35,7 +35,7 @@ jobs:
matrix:
part: [0, 1]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -70,7 +70,6 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
pip install sentence_transformers accelerate
cd test
python3 run_suite.py --hw npu --suite nightly-1-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
@@ -83,7 +82,7 @@ jobs:
matrix:
part: [0]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -118,7 +117,6 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
pip install sentence_transformers accelerate
cd test
python3 run_suite.py --hw npu --suite nightly-2-npu-a3 --nightly --continue-on-error --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 1
@@ -131,7 +129,7 @@ jobs:
matrix:
part: [0]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -144,8 +142,7 @@ jobs:
CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
sed -Ei "s@(ports|archive).ubuntu.com@${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"
pip config set global.trusted-host "${CACHING_URL}"
bash scripts/ci/npu/npu_ci_install_dependency.sh a3
# copy required file from our daily cache
@@ -167,7 +164,6 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
hf download lmms-lab/MMMU --repo-type dataset
pip install sentence_transformers torchaudio==2.8.0 torch_npu==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
.github/workflows/pr-test-npu.yml
+4 -8
View File
@@ -79,7 +79,7 @@ jobs:
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-1
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -111,7 +111,6 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
cd test/srt
python3 run_suite.py --suite per-commit-1-npu-a2
@@ -124,7 +123,7 @@ jobs:
matrix:
part: [0, 1, 2]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -156,7 +155,6 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
cd test/srt
python3 run_suite.py --suite per-commit-2-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3
@@ -165,7 +163,7 @@ jobs:
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-4
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -197,7 +195,6 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
cd test/srt
python3 run_suite.py --suite per-commit-4-npu-a2 --timeout-per-file 3600
@@ -210,7 +207,7 @@ jobs:
matrix:
part: [0, 1]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -242,6 +239,5 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
STREAMS_PER_DEVICE: 32
run: |
export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
cd test/srt
python3 run_suite.py --suite per-commit-16-npu-a3 --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
.github/workflows/release-docker-npu-nightly.yml
+2 -2
View File
@@ -13,7 +13,7 @@ jobs:
runs-on: ubuntu-22.04-arm
strategy:
matrix:
cann_version: ["8.3.rc2"]
cann_version: ["8.5.0"]
device_type: ["910b", "a3"]
steps:
- name: Checkout repository
@@ -67,6 +67,6 @@ jobs:
push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
provenance: false
build-args: |
SGLANG_KERNEL_NPU_TAG=2025.12.31
SGLANG_KERNEL_NPU_TAG=2026.01.21
CANN_VERSION=${{ 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: ["8.3.rc2"]
cann_version: ["8.5.0"]
device_type: ["910b", "a3"]
steps:
- name: Checkout repository
@@ -81,7 +81,7 @@ jobs:
push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
provenance: false
build-args: |
SGLANG_KERNEL_NPU_TAG=2025.12.31
SGLANG_KERNEL_NPU_TAG=2026.01.21
CANN_VERSION=${{ matrix.cann_version }}
DEVICE_TYPE=${{ matrix.device_type }}
SGLANG_TAG=${{ steps.version.outputs.version }}