EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Files
0fbe0831ecfd908ab7e38d2bd86cc7818b22e58d
xc-llm-ascend/.github/workflows/_e2e_test.yaml
SILONG ZENG e56dba9b0d [CI]cleanup e2e test (#4800) 
### What this PR does / why we need it?
This PR refactors the E2E multicard test suite to improve test case
identification and maintainability. Specifically, it renames various
test functions to be more descriptive (explicitly indicating model
families like Qwen/DeepSeek and parallelism strategies like DP/TP/PP/EP)
and cleans up outdated or redundant test configurations in the offline
distributed inference tests.

**Key Changes:**
1. Test Function Renaming (Standardization): Renamed multiple test
functions across **`tests/e2e/multicard/`** to include clear
suffixes/prefixes regarding the model and parallel strategy. This helps
differentiate test cases in CI logs and prevents naming collisions.

**`test_aclgraph_capture_replay.py`:** 
- `test_aclgraph_capture_replay_dp2` ->
`test_aclgraph_capture_replay_metrics_dp2`

**`test_data_parallel.py`:**
- `test_data_parallel_inference` -> `test_qwen_inference_dp2`

**`test_data_parallel_tp2.py`:**
- `test_data_parallel_inference` -> `test_qwen_inference_dp2_tp2`

**`test_expert_parallel.py`:**
- `test_e2e_ep_correctness` -> `test_deepseek_correctness_ep`

**`test_external_launcher.py`:**
- `test_external_launcher` -> `test_qwen_external_launcher`
- `test_moe_external_launcher` -> `test_qwen_moe_external_launcher_ep`
- `test_external_launcher_and_sleepmode` ->
`test_qwen_external_launcher_with_sleepmode`
- `test_external_launcher_and_sleepmode_level2` ->
`test_qwen_external_launcher_with_sleepmode_level2`
- `test_mm_allreduce` ->
`test_qwen_external_launcher_with_matmul_allreduce`

**`test_full_graph_mode.py`:** 
- `test_models_distributed_Qwen3_MOE_TP2_WITH_FULL_DECODE_ONLY` ->
`test_qwen_moe_with_full_decode_only`
- `test_models_distributed_Qwen3_MOE_TP2_WITH_FULL` ->
`test_qwen_moe_with_full`

**`test_fused_moe_allgather_ep.py`:** 
- `test_generate_with_allgather `->
`test_deepseek_moe_fused_allgather_ep`
- `test_generate_with_alltoall` -> `test_deepseek_moe_fused_alltoall_ep`

**`test_offline_weight_load.py`:**
- `test_offline_weight_load_and_sleepmode` ->
`test_qwen_offline_weight_load_and_sleepmode`

**`test_pipeline_parallel.py`:**
- `test_models` -> `test_models_pp2`

2. Distributed Inference Cleanup
(**`test_offline_inference_distributed.py`**):

**model list changes:**
```
QWEN_DENSE_MODELS = [
-     "vllm-ascend/Qwen3-8B-W8A8", "vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8"
+     "vllm-ascend/Qwen3-8B-W8A8",
]
```

```
- QWEN_W4A8_OLD_VERSION_MODELS = [
-    "vllm-ascend/Qwen3-8B-W4A8",
- ]

- QWEN_W4A8_NEW_VERSION_MODELS = [
-     "vllm-ascend/DeepSeek-V3-W4A8-Pruing",
-     "vllm-ascend/DeepSeek-V3.1-W4A8-puring",
- ]

+ DEEPSEEK_W4A8_MODELS = [
+      "vllm-ascend/DeepSeek-V3.1-W4A8-puring",
+ ]
```

**Test Function Changes:**
- removed `test_models_distributed_QwQ`
- removed `test_models_distributed_Qwen3_W8A8`
- removed `test_models_distributed_Qwen3_W4A8DYNAMIC_old_version`
- `test_models_distributed_Qwen3_W4A8DYNAMIC_new_version` ->
`test_models_distributed_Qwen3_W4A8DYNAMIC`

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
2025-12-11 20:35:32 +08:00

287 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: ${{ inputs.image }}
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
TRANSFORMERS_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(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@v6.0.1
- 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@v6.0.1
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_accuracy.py
# pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
pytest -sv tests/e2e/singlecard/pooling/test_classification.py::test_classify_correctness
- name: Run e2e test
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_USE_MODELSCOPE: True
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
if: ${{ inputs.type == 'full' }}
run: |
# We found that if running aclgraph tests in batch, it will cause AclmdlRICaptureBegin error. So we run
# the test separately.
pytest -sv tests/e2e/singlecard/test_completion_with_prompt_embeds.py
pytest -sv tests/e2e/singlecard/test_aclgraph_accuracy.py
pytest -sv tests/e2e/singlecard/test_aclgraph_mem.py
pytest -sv tests/e2e/singlecard/test_camem.py
pytest -sv tests/e2e/singlecard/test_guided_decoding.py
# torch 2.8 doesn't work with lora, fix me
#pytest -sv tests/e2e/singlecard/test_ilama_lora.py
pytest -sv tests/e2e/singlecard/test_profile_execute_duration.py
pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_sampler.py
pytest -sv tests/e2e/singlecard/test_vlm.py
pytest -sv tests/e2e/singlecard/test_xlite.py
pytest -sv tests/e2e/singlecard/pooling/
pytest -sv tests/e2e/singlecard/compile/test_norm_quant_fusion.py
# ------------------------------------ v1 spec decode test ------------------------------------ #
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
e2e-2-cards:
name: multicard-2
runs-on: linux-aarch64-a3-2
container:
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
HCCL_BUFFSIZE: 1024
TRANSFORMERS_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
- name: Config mirrors
run: |
# Fix me: use nginx cache rather than the pypi
# 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
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
apt-get update -y
apt install git -y
- name: Checkout vllm-project/vllm-ascend repo
uses: actions/checkout@v6.0.1
- 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@v6.0.1
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
- 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_quantization.py
pytest -sv tests/e2e/multicard/test_aclgraph_capture_replay.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
# torch 2.8 doesn't work with lora, fix me
#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_DeepSeek_multistream_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC
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
pytest -sv tests/e2e/multicard/test_offline_weight_load.py
e2e-4-cards:
name: multicard-4
needs: [e2e, e2e-2-cards]
if: ${{ needs.e2e.result == 'success' && needs.e2e-2-cards.result == 'success' && inputs.type == 'full' }}
runs-on: linux-aarch64-a3-4
container:
image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
env:
VLLM_LOGGING_LEVEL: ERROR
VLLM_USE_MODELSCOPE: True
TRANSFORMERS_OFFLINE: 1
steps:
- name: Check npu and CANN info
run: |
npu-smi info
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
- name: Config mirrors
run: |
sed -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@v6.0.1
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@v6.0.1
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
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_models_distributed_Kimi_K2_Thinking_W4A16
# pytest -sv tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_TP2_WITH_EP
# pytest -sv tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_W8A8_WITH_EP
pytest -sv tests/e2e/multicard/test_data_parallel_tp2.py
- name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct)
shell: bash -l {0}
run: |
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/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.dev2025110717-cp311-cp311-manylinux_2_27_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/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
pytest -sv tests/e2e/multicard/test_qwen3_next.py
Reference in New Issue View Git Blame Copy Permalink