EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Files
2938bd5ad20c6619e6dbf247d2e8bfa99de571d5
xc-llm-ascend/.github/workflows/_e2e_test.yaml
XiaoxinWang e38ef2c434 support FULL graph mode for GQA (#3970) 
### What this PR does / why we need it?
The current library only supports the FullDecodeOnly graph mode, which
enables full graph execution during the decode. This PR extends support
to allow full graph execution in both the prefill and decode, referred
to as FULL graph mode.

- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
2025-11-17 10:50:35 +08:00

288 lines
12 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
jobs:
e2e:
name: singlecard
runs-on: ${{ inputs.runner }}-1
container:
image: ${{ inputs.image }}
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(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@v4
- 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@v4
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:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_USE_MODELSCOPE: True
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
if: ${{ inputs.type == 'light' }}
run: |
# pytest -sv tests/e2e/singlecard/test_aclgraph.py
# pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
- name: Run e2e test
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_USE_MODELSCOPE: True
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.
pytest -sv tests/e2e/singlecard/test_completion_with_prompt_embeds.py
pytest -sv tests/e2e/singlecard/test_aclgraph.py
pytest -sv tests/e2e/singlecard/test_aclgraph_mem.py
pytest -sv tests/e2e/singlecard/test_ascend_scheduler.py
pytest -sv tests/e2e/singlecard/test_bge_model.py
pytest -sv tests/e2e/singlecard/test_camem.py
pytest -sv tests/e2e/singlecard/test_chunked.py
pytest -sv tests/e2e/singlecard/test_embedding.py
# pytest -sv tests/e2e/singlecard/test_embedding_aclgraph.py
pytest -sv tests/e2e/singlecard/test_guided_decoding.py
pytest -sv tests/e2e/singlecard/test_ilama_lora.py
pytest -sv tests/e2e/singlecard/test_profile_execute_duration.py
pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_sampler.py
pytest -sv tests/e2e/singlecard/test_vlm.py
pytest -sv tests/e2e/singlecard/multi-modal/test_internvl.py
# ------------------------------------ v1 spec decode test ------------------------------------ #
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_torchair_correctness.py
# Fix me: test_eagle_correctness OOM error
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
# TODO: Move ops test to nightly test
#pytest -sv tests/e2e/singlecard/ops/
e2e-2-cards:
name: multicard-2
runs-on: ${{ inputs.runner }}-2
container:
image: ${{ inputs.image }}
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(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@v4
- 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@v4
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
VLLM_USE_MODELSCOPE: True
if: ${{ inputs.type == 'light' }}
run: |
pytest -sv tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_TP2_WITH_EP
pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py::test_e2e_deepseekv2lite_with_torchair
- name: Run vllm-project/vllm-ascend test (full)
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_USE_MODELSCOPE: True
if: ${{ inputs.type == 'full' }}
run: |
pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py
pytest -sv tests/e2e/multicard/test_full_graph_mode.py
pytest -sv tests/e2e/multicard/test_data_parallel.py
pytest -sv tests/e2e/multicard/test_expert_parallel.py
pytest -sv tests/e2e/multicard/test_external_launcher.py
pytest -sv tests/e2e/multicard/test_single_request_aclgraph.py
pytest -sv tests/e2e/multicard/test_fused_moe_allgather_ep.py
pytest -sv tests/e2e/multicard/test_ilama_lora_tp2.py
# 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_QwQ
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_Qwen3_W8A8
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC_new_version
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC_old_version
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_sp_for_qwen3_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_fc2_for_qwen3_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_flashcomm_v1
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_prefetch_mlp_weight
pytest -sv tests/e2e/multicard/test_pipeline_parallel.py
pytest -sv tests/e2e/multicard/test_prefix_caching.py
pytest -sv tests/e2e/multicard/test_qwen3_moe.py
e2e-4-cards:
name: multicard-4
runs-on: linux-aarch64-a3-4
container:
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
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 -i 's|ports.ubuntu.com|mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
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@v4
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
- name: Checkout vllm-project/vllm repo
uses: actions/checkout@v4
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
VLLM_USE_MODELSCOPE: True
run: |
pytest -sv \
tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe \
tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
# tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_TP2_WITH_EP \
# tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_W8A8_WITH_EP
- name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct)
shell: bash -l {0}
run: |
wget -q https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run -O /tmp/Ascend-BiSheng-toolkit_aarch64.run
chmod a+x /tmp/Ascend-BiSheng-toolkit_aarch64.run
/tmp/Ascend-BiSheng-toolkit_aarch64.run --install
. /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
- name: Run vllm-project/vllm-ascend Qwen3 Next test
working-directory: ./vllm-ascend
shell: bash -el {0}
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_USE_MODELSCOPE: True
run: |
. /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
pytest -sv tests/e2e/multicard/test_qwen3_next.py
Reference in New Issue View Git Blame Copy Permalink