e56dba9b0d
### 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and cleans up outdated or redundant test configurations in the offline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>
75 lines
2.5 KiB
Python
75 lines
2.5 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# Copyright 2023 The vLLM team.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
"""
|
|
Execute the inference of fused_moe_allgather_ep and fused_moe_alltoall_ep.
|
|
|
|
Run 'pytest tests/multicard/test_fused_moe_allgather_ep.py'.
|
|
"""
|
|
|
|
import os
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
from modelscope import snapshot_download # type: ignore
|
|
from vllm import SamplingParams
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
True,
|
|
reason=
|
|
"Current disaggregated pd implementation may cause memory pulse, which will cause this test OOM, skip this test until the ringmla is ready "
|
|
)
|
|
@patch.dict(
|
|
os.environ, {
|
|
"VLLM_WORKER_MULTIPROC_METHOD": "spawn",
|
|
"TASK_QUEUE_ENABLE": "1",
|
|
"VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP": "1"
|
|
})
|
|
def test_deepseek_moe_fused_allgather_ep():
|
|
example_prompts = ["Hello, my name is"]
|
|
sampling_params = SamplingParams(max_tokens=100, temperature=0.0)
|
|
|
|
with VllmRunner(snapshot_download("vllm-ascend/DeepSeek-V3-Pruning"),
|
|
tensor_parallel_size=2,
|
|
max_model_len=1024,
|
|
dtype="auto",
|
|
enable_expert_parallel=True) as vllm_model:
|
|
vllm_model.generate(example_prompts, sampling_params)
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
True,
|
|
reason=
|
|
"Current disaggregated pd implementation may cause memory pulse, which will cause this test OOM, skip this test until the ringmla is ready "
|
|
)
|
|
@patch.dict(os.environ, {
|
|
"VLLM_WORKER_MULTIPROC_METHOD": "spawn",
|
|
"TASK_QUEUE_ENABLE": "1"
|
|
})
|
|
def test_deepseek_moe_fused_alltoall_ep():
|
|
example_prompts = ["Hello, my name is"]
|
|
sampling_params = SamplingParams(max_tokens=100, temperature=0.0)
|
|
|
|
with VllmRunner(snapshot_download("vllm-ascend/DeepSeek-V3-Pruning"),
|
|
tensor_parallel_size=2,
|
|
max_model_len=1024,
|
|
dtype="auto",
|
|
enable_expert_parallel=True) as vllm_model:
|
|
vllm_model.generate(example_prompts, sampling_params)
|