[NPU]Optimize the PR pipeline to reduce E2E runtime (#18767)

Co-authored-by: Sugar920 <121632458+Sugar920@users.noreply.github.com>
This commit is contained in:
Cherry_ming
2026-02-28 17:06:03 +08:00
committed by GitHub
co-authored by Sugar920
parent 366574b2b8
commit 1eb40d8d45
12 changed files with 17 additions and 238 deletions
+14 -14
View File
@@ -79,6 +79,10 @@ jobs:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-1
strategy:
fail-fast: false
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
steps:
@@ -113,7 +117,7 @@ jobs:
STREAMS_PER_DEVICE: 32
run: |
cd test/srt
python3 run_suite.py --suite per-commit-1-npu-a2
python3 run_suite.py --suite per-commit-1-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
per-commit-2-npu-a2:
needs: [check-changes, pr-gate]
@@ -122,7 +126,7 @@ jobs:
strategy:
fail-fast: true
matrix:
part: [0, 1, 2]
part: [0, 1]
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
steps:
@@ -157,14 +161,14 @@ jobs:
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 3
python3 run_suite.py --suite per-commit-2-npu-a2 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
per-commit-4-npu-a2:
per-commit-4-npu-a3:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a2-4
runs-on: linux-aarch64-a3-4
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -180,7 +184,7 @@ jobs:
pip config set global.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple"
pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn"
bash scripts/ci/npu/npu_ci_install_dependency.sh 910b
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
@@ -197,16 +201,12 @@ jobs:
STREAMS_PER_DEVICE: 32
run: |
cd test/srt
python3 run_suite.py --suite per-commit-4-npu-a2 --timeout-per-file 3600
python3 run_suite.py --suite per-commit-4-npu-a3 --timeout-per-file 3600
per-commit-16-npu-a3:
needs: [check-changes, pr-gate]
if: needs.check-changes.outputs.main_package == 'true'
runs-on: linux-aarch64-a3-16
strategy:
fail-fast: true
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
steps:
@@ -241,12 +241,12 @@ jobs:
STREAMS_PER_DEVICE: 32
run: |
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
python3 run_suite.py --suite per-commit-16-npu-a3 --timeout-per-file 3600
multimodal-gen-test-1-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-a3-2
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
steps: