EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Files
f8e76a49facd2e7877a039634f07e1292d1ccb7e
xc-llm-ascend/.github/workflows/_e2e_test.yaml
wangxiyuan f8e76a49fa [CI] Upgrade trasnformers version (#6307) 
Upgrade transformers to >=4.56.4

- vLLM version: v0.14.1
- vLLM main:
dc917cceb8

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2026-01-28 14:06:39 +08:00

431 lines
18 KiB
YAML
Raw Blame History

name: 'e2e test'
on:
workflow_call:
inputs:
vllm:
required: true
type: string
runner:
required: true
type: string
image:
required: true
type: string
type:
required: true
type: string
contains_310:
required: true
type: boolean
jobs:
e2e:
name: singlecard
runs-on: linux-aarch64-a2b3-1
container:
image: ${{ inputs.image }}
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
HF_HUB_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
- name: Config mirrors
run: |
sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
apt-get update -y
apt install git -y
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v6
- name: Install system dependencies
run: |
apt-get -y install `cat packages.txt`
apt-get -y install gcc g++ cmake libnuma-dev clang-15
update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20
update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v6
with:
repository: vllm-project/vllm
ref: ${{ inputs.vllm }}
path: ./vllm-empty
fetch-depth: 1
- name: Install vllm-project/vllm from source
working-directory: ./vllm-empty
run: |
VLLM_TARGET_DEVICE=empty pip install -e .
- name: Install vllm-project/vllm-ascend
env:
PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
run: |
pip install -r requirements-dev.txt
pip install -v -e .
- name: Run vllm-project/vllm-ascend test
env:
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
VLLM_WORKER_MULTIPROC_METHOD: spawn
if: ${{ inputs.type == 'light' }}
run: |
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_accuracy.py::test_piecewise_res_consistency
pytest -sv --durations=0 tests/e2e/singlecard/test_quantization.py::test_qwen3_w8a8_quant
- name: Run e2e test
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
if: ${{ inputs.type == 'full' }}
run: |
# We found that if running aclgraph tests in batch, it will cause AclmdlRICaptureBegin error. So we run
# the test separately.
# basic
pytest -sv --durations=0 tests/e2e/singlecard/test_auto_fit_max_mode_len.py
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_accuracy.py
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_batch_invariant.py
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_mem.py
pytest -sv --durations=0 tests/e2e/singlecard/test_async_scheduling.py
pytest -sv --durations=0 tests/e2e/singlecard/test_batch_invariant.py
pytest -sv --durations=0 tests/e2e/singlecard/test_camem.py
pytest -sv --durations=0 tests/e2e/singlecard/test_completion_with_prompt_embeds.py
pytest -sv --durations=0 tests/e2e/singlecard/test_cpu_offloading.py
pytest -sv --durations=0 tests/e2e/singlecard/test_guided_decoding.py
pytest -sv --durations=0 tests/e2e/singlecard/test_ilama_lora.py
pytest -sv --durations=0 tests/e2e/singlecard/test_llama32_lora.py
pytest -sv --durations=0 tests/e2e/singlecard/test_qwen3_multi_loras.py
pytest -sv --durations=0 tests/e2e/singlecard/test_models.py
pytest -sv --durations=0 tests/e2e/singlecard/test_multistream_overlap_shared_expert.py
pytest -sv --durations=0 tests/e2e/singlecard/test_profile_execute_duration.py
pytest -sv --durations=0 tests/e2e/singlecard/test_quantization.py
pytest -sv --durations=0 tests/e2e/singlecard/test_sampler.py
pytest -sv --durations=0 tests/e2e/singlecard/test_vlm.py
pytest -sv --durations=0 tests/e2e/singlecard/test_xlite.py
# compile
pytest -sv --durations=0 tests/e2e/singlecard/compile/test_norm_quant_fusion.py
# model_runner_v2
# pytest -sv --durations=0 tests/e2e/singlecard/model_runner_v2/test_basic.py
# pooling
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_classification.py
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_embedding.py
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_scoring.py
# spec_decode
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode/test_mtp_eagle_correctness.py
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py
e2e-2-cards:
name: multicard-2
runs-on: linux-aarch64-a3-2
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
HCCL_BUFFSIZE: 1024
HF_HUB_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
- name: Config mirrors
run: |
sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
apt-get update -y
apt install git -y
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v6
- name: Install system dependencies
run: |
apt-get -y install `cat packages.txt`
apt-get -y install gcc g++ cmake libnuma-dev clang-15
update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20
update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v6
with:
repository: vllm-project/vllm
ref: ${{ inputs.vllm }}
path: ./vllm-empty
fetch-depth: 1
- name: Install vllm-project/vllm from source
working-directory: ./vllm-empty
run: |
VLLM_TARGET_DEVICE=empty pip install -e .
- name: Install vllm-project/vllm-ascend
env:
PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
run: |
pip install -r requirements-dev.txt
pip install -v -e .
- name: Run vllm-project/vllm-ascend test (light)
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
if: ${{ inputs.type == 'light' }}
run: |
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_qwen3_moe.py::test_qwen3_moe_distributed_mp_tp2_ep
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek3_2_w8a8_pruning_mtp_tp2_ep
- name: Run vllm-project/vllm-ascend test (full)
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
if: ${{ inputs.type == 'full' }}
run: |
# this test fail with triton. Fix me.
# pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_qwen3_performance.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_data_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_expert_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_external_launcher.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_full_graph_mode.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_ilama_lora_tp2.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/spec_decode/test_spec_decode.py
# To avoid oom, we need to run the test in a single process.
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_multistream_moe_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_w4a8_dynamic_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_moe_sp_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_w4a8_accuracy_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_moe_fc2_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_v2_lite_fc1_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_dense_fc1_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_dense_prefetch_mlp_weight_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek3_2_w8a8_pruning_mtp_tp2_ep
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_w4a4_distributed_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_weight_load.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_pipeline_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_prefix_caching.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_quantization.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_qwen3_moe.py
# This test is broken, fix me
#pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_shared_expert_dp.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_single_request_aclgraph.py
- name: Run vllm-project/vllm-ascend test (non triton)
if: ${{ inputs.type == 'full' }}
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
run: |
python3 -m pip uninstall -y triton-ascend
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py
e2e-4-cards:
name: multicard-4
needs: [e2e-2-cards]
if: ${{ needs.e2e-2-cards.result == 'success' && inputs.type == 'full' }}
runs-on: linux-aarch64-a3-4
container:
image: m.daocloud.io/quay.io/ascend/cann:8.5.0-a3-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
HF_HUB_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
- name: Config mirrors
run: |
sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
apt-get update -y
apt install git wget curl -y
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@v6
with:
path: ./vllm-ascend
- name: Install system dependencies
run: |
apt-get -y install `cat packages.txt`
apt-get -y install gcc g++ cmake libnuma-dev clang-15
update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20
update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v6
with:
repository: vllm-project/vllm
ref: ${{ inputs.vllm }}
path: ./vllm-empty
- name: Install vllm-project/vllm from source
working-directory: ./vllm-empty
run: |
VLLM_TARGET_DEVICE=empty pip install -e .
- name: Install vllm-project/vllm-ascend
working-directory: ./vllm-ascend
run: |
export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
pip install -r requirements-dev.txt
pip install -v -e .
- name: Run vllm-project/vllm-ascend test for V1 Engine
working-directory: ./vllm-ascend
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
run: |
pytest -sv --durations=0 tests/e2e/multicard/4-cards/test_data_parallel_tp2.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/test_kimi_k2.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/test_qwen3_next.py
# recover once aclgraph stream bug fixed.
# long_sequence
# pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_accuracy.py
# pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_basic.py
# pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_chunked_prefill.py
# pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_mtp.py
# # spec_decode
# pytest -sv --durations=0 tests/e2e/multicard/4-cards/spec_decode/test_mtp_qwen3_next.py
e2e_310p:
name: 310p singlecard
runs-on: linux-aarch64-310p-1
if: ${{ inputs.contains_310 }}
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-310p-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
HF_HUB_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
- name: Config mirrors
run: |
sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
apt-get update -y
apt install git -y
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v6
- name: Install system dependencies
run: |
apt-get -y install `cat packages.txt`
apt-get -y install gcc g++ cmake libnuma-dev
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v6
with:
repository: vllm-project/vllm
ref: ${{ inputs.vllm }}
path: ./vllm-empty
fetch-depth: 1
- name: Install vllm-project/vllm from source
working-directory: ./vllm-empty
run: |
VLLM_TARGET_DEVICE=empty pip install -e .
- name: Install vllm-project/vllm-ascend
env:
PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
run: |
pip install -r requirements-dev.txt
pip install -v -e .
- name: Run vllm-project/vllm-ascend test
env:
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
VLLM_WORKER_MULTIPROC_METHOD: spawn
run: |
pytest -sv --durations=0 tests/e2e/310p/test_offline_inference_310p.py
e2e_310p-4cards:
name: 310p multicards 4cards
runs-on: linux-aarch64-310p-4
if: ${{ inputs.contains_310 }}
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-310p-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
HF_HUB_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
- name: Config mirrors
run: |
sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
apt-get update -y
apt install git -y
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v6
- name: Install system dependencies
run: |
apt-get -y install `cat packages.txt`
apt-get -y install gcc g++ cmake libnuma-dev
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v6
with:
repository: vllm-project/vllm
ref: ${{ inputs.vllm }}
path: ./vllm-empty
fetch-depth: 1
- name: Install vllm-project/vllm from source
working-directory: ./vllm-empty
run: |
VLLM_TARGET_DEVICE=empty pip install -e .
- name: Install vllm-project/vllm-ascend
env:
PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
run: |
pip install -r requirements-dev.txt
pip install -v -e .
- name: Run vllm-project/vllm-ascend test
env:
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
VLLM_WORKER_MULTIPROC_METHOD: spawn
run: |
pytest -sv --durations=0 tests/e2e/310p/test_offline_inference_parallel_310p.py
Reference in New Issue View Git Blame Copy Permalink