EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[CI] fix ci (#2464)

Browse Source 
### What this PR does / why we need it?
1. use action/checkout@v5 instead of v4
2. remove dbo test case because there is issue with it and will be
refactored later
3. make vllm-ascend compatible with vllm v0.10.1.1 and add CI for it
4. fix sampler api changes introduced by
https://github.com/vllm-project/vllm/pull/22387
6. fix qwen3 moe config changes intruoduced by
https://github.com/vllm-project/vllm/pull/20562
7. fix kvcache block changes introduced by
https://github.com/vllm-project/vllm/pull/23262

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with existing test.


- vLLM version: v0.10.0
- vLLM main:
0c6e40bbaa

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-08-22 07:30:48 +08:00
committed by GitHub
parent 0ca3f48c90
commit b0403f8d8a
27 changed files with 389 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.github/workflows/accuracy_test.yaml vendored
View File

@@ -88,7 +88,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@v5
uses: actions/checkout@v4
- name: Set model name as output
id: set_output
@@ -109,7 +109,7 @@ jobs:
apt-get -y install gcc g++ cmake libnuma-dev
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm
ref: v0.10.0
@@ -138,7 +138,7 @@ jobs:
echo "GHA_VLLM_ASCEND_VERSION=$RESOLVED_VERSION" >> $GITHUB_ENV
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm-ascend
path: ./vllm-ascend
@@ -236,7 +236,7 @@ jobs:
UPSTREAM_REPO: vllm-project/vllm-ascend
steps:
- name: Checkout repository
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-ascend-ci/vllm-ascend
token: ${{ secrets.PAT_TOKEN }}

2
.github/workflows/format_pr_body.yaml vendored
View File

@@ -34,7 +34,7 @@ jobs:
steps:
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm
path: ./vllm-empty

2
.github/workflows/image_310p_openeuler.yml vendored
View File

@@ -53,7 +53,7 @@ jobs:
'ubuntu-24.04-arm'
}}
steps:
- uses: actions/checkout@v5
- uses: actions/checkout@v4
- name: Print
run: |

2
.github/workflows/image_310p_ubuntu.yml vendored
View File

@@ -49,7 +49,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v5
- uses: actions/checkout@v4
- name: Print
run: |

2
.github/workflows/image_a3_openeuler.yml vendored
View File

@@ -53,7 +53,7 @@ jobs:
'ubuntu-24.04-arm'
}}
steps:
- uses: actions/checkout@v5
- uses: actions/checkout@v4
- name: Print
run: |

2
.github/workflows/image_a3_ubuntu.yml vendored
View File

@@ -49,7 +49,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v5
- uses: actions/checkout@v4
- name: Print
run: |

2
.github/workflows/image_openeuler.yml vendored
View File

@@ -52,7 +52,7 @@ jobs:
'ubuntu-24.04-arm'
}}
steps:
- uses: actions/checkout@v5
- uses: actions/checkout@v4
- name: Print
run: |

2
.github/workflows/image_ubuntu.yml vendored
View File

@@ -49,7 +49,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v5
- uses: actions/checkout@v4
- name: Print
run: |

4
.github/workflows/nightly_benchmarks.yaml vendored
View File

@@ -97,12 +97,12 @@ jobs:
git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm
path: ./vllm-empty

4
.github/workflows/pre-commit.yml vendored
View File

@@ -11,14 +11,14 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v5
uses: actions/checkout@v4
- uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
with:
python-version: "3.11"
- run: echo "::add-matcher::.github/workflows/matchers/actionlint.json"
- run: echo "::add-matcher::.github/workflows/matchers/mypy.json"
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm
path: ./vllm-empty

2
.github/workflows/vllm_ascend_doctest.yaml vendored
View File

@@ -66,7 +66,7 @@ jobs:
git --no-pager log -1 || true
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v5
uses: actions/checkout@v4
- name: Run vllm-ascend/tests/e2e/run_doctests.sh
run: |

11
.github/workflows/vllm_ascend_test.yaml vendored
View File

@@ -81,7 +81,7 @@ jobs:
VLLM_USE_MODELSCOPE: True
strategy:
matrix:
vllm_version: [main]
vllm_version: [v0.10.1.1, main]
steps:
- name: Install packages
run: |
@@ -89,7 +89,7 @@ jobs:
apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev curl gnupg2
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm
ref: ${{ matrix.vllm_version }}
@@ -102,7 +102,7 @@ jobs:
python3 -m pip uninstall -y triton
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v5
uses: actions/checkout@v4
- name: Install vllm-project/vllm-ascend
run: |
@@ -137,7 +137,7 @@ jobs:
max-parallel: 2
matrix:
os: [linux-aarch64-a2-1]
vllm_version: [main]
vllm_version: [v0.10.1.1, main]
name: singlecard e2e test
runs-on: ${{ matrix.os }}
container:
@@ -219,7 +219,7 @@ jobs:
max-parallel: 2
matrix:
os: [linux-aarch64-a2-2]
vllm_version: [main]
vllm_version: [v0.10.1.1, main]
name: multicard e2e test
runs-on: ${{ matrix.os }}
container:
@@ -278,7 +278,6 @@ jobs:
# To avoid oom, we need to run the test in a single process.
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_dbo
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeekV3_dbo
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_alltoallv
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC

6
.github/workflows/vllm_ascend_test_310p.yaml vendored
View File

@@ -53,7 +53,7 @@ jobs:
max-parallel: 2
matrix:
os: [linux-aarch64-310p-1, linux-aarch64-310p-4]
vllm_version: [main]
vllm_version: [v0.10.1.1, main]
name: 310p e2e test
runs-on: ${{ matrix.os }}
container:
@@ -77,7 +77,7 @@ jobs:
apt install git -y
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v5
uses: actions/checkout@v4
- name: Install system dependencies
run: |
@@ -85,7 +85,7 @@ jobs:
apt-get -y install git vim wget net-tools gcc g++ cmake libnuma-dev curl gnupg2
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm
ref: ${{ matrix.vllm_version }}

4
.github/workflows/vllm_ascend_test_pd.yaml vendored
View File

@@ -80,7 +80,7 @@ jobs:
git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v5
uses: actions/checkout@v4
- name: Install system dependencies
run: |
@@ -88,7 +88,7 @@ jobs:
apt-get -y install gcc g++ cmake libnuma-dev
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v5
uses: actions/checkout@v4
with:
repository: vllm-project/vllm
ref: ${{ matrix.vllm_verison }}