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and cleans up outdated or redundant test configurations in the offline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>
122 lines
4.3 KiB
Python
122 lines
4.3 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.
|
|
# This file is a part of the vllm-ascend project.
|
|
# Adapted from vllm/tests/basic_correctness/test_basic_correctness.py
|
|
#
|
|
"""Compare the short outputs of HF and vLLM when using greedy sampling.
|
|
|
|
Run `pytest tests/e2e/multicard/test_qwen3_moe.py`.
|
|
"""
|
|
|
|
import os
|
|
|
|
from vllm import SamplingParams
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
from tests.e2e.model_utils import check_outputs_equal
|
|
|
|
|
|
def test_qwen_moe_with_full_decode_only():
|
|
if 'HCCL_OP_EXPANSION_MODE' in os.environ:
|
|
del os.environ['HCCL_OP_EXPANSION_MODE']
|
|
prompts = [
|
|
"Hello, my name is", "The president of the United States is",
|
|
"The capital of France is", "The future of AI is"
|
|
]
|
|
model = "Qwen/Qwen3-30B-A3B"
|
|
sampling_params = SamplingParams(max_tokens=32, temperature=0.0)
|
|
with VllmRunner(model,
|
|
max_model_len=1024,
|
|
tensor_parallel_size=2,
|
|
enforce_eager=False,
|
|
compilation_config={
|
|
"cudagraph_mode": "FULL_DECODE_ONLY",
|
|
"cudagraph_capture_sizes": [4, 8, 24, 48, 60]
|
|
}) as runner:
|
|
vllm_fullgraph_outputs = runner.model.generate(prompts,
|
|
sampling_params)
|
|
|
|
with VllmRunner(
|
|
model,
|
|
max_model_len=1024,
|
|
tensor_parallel_size=2,
|
|
enforce_eager=False,
|
|
) as runner:
|
|
vllm_eager_outputs = runner.model.generate(prompts, sampling_params)
|
|
|
|
vllm_fullgraph_outputs_list = []
|
|
for output in vllm_fullgraph_outputs:
|
|
vllm_fullgraph_outputs_list.append(
|
|
(output.outputs[0].index, output.outputs[0].text))
|
|
|
|
vllm_eager_outputs_list = []
|
|
for output in vllm_eager_outputs:
|
|
vllm_eager_outputs_list.append(
|
|
(output.outputs[0].index, output.outputs[0].text))
|
|
|
|
check_outputs_equal(
|
|
outputs_0_lst=vllm_eager_outputs_list,
|
|
outputs_1_lst=vllm_fullgraph_outputs_list,
|
|
name_0="vllm_eager_outputs",
|
|
name_1="vllm_fullgraph_outputs",
|
|
)
|
|
|
|
|
|
def test_qwen_moe_with_full():
|
|
if 'HCCL_OP_EXPANSION_MODE' in os.environ:
|
|
del os.environ['HCCL_OP_EXPANSION_MODE']
|
|
prompts = [
|
|
"Hello, my name is", "The president of the United States is",
|
|
"The capital of France is", "The future of AI is"
|
|
]
|
|
model = "Qwen/Qwen3-30B-A3B"
|
|
sampling_params = SamplingParams(max_tokens=32, temperature=0.0)
|
|
with VllmRunner(model,
|
|
max_model_len=1024,
|
|
tensor_parallel_size=2,
|
|
enforce_eager=False,
|
|
compilation_config={
|
|
"cudagraph_mode": "FULL",
|
|
"cudagraph_capture_sizes": [4, 8, 24, 48, 60]
|
|
}) as runner:
|
|
vllm_fullgraph_outputs = runner.model.generate(prompts,
|
|
sampling_params)
|
|
|
|
with VllmRunner(
|
|
model,
|
|
max_model_len=1024,
|
|
tensor_parallel_size=2,
|
|
enforce_eager=False,
|
|
) as runner:
|
|
vllm_eager_outputs = runner.model.generate(prompts, sampling_params)
|
|
|
|
vllm_fullgraph_outputs_list = []
|
|
for output in vllm_fullgraph_outputs:
|
|
vllm_fullgraph_outputs_list.append(
|
|
(output.outputs[0].index, output.outputs[0].text))
|
|
|
|
vllm_eager_outputs_list = []
|
|
for output in vllm_eager_outputs:
|
|
vllm_eager_outputs_list.append(
|
|
(output.outputs[0].index, output.outputs[0].text))
|
|
|
|
check_outputs_equal(
|
|
outputs_0_lst=vllm_eager_outputs_list,
|
|
outputs_1_lst=vllm_fullgraph_outputs_list,
|
|
name_0="vllm_eager_outputs",
|
|
name_1="vllm_fullgraph_outputs",
|
|
)
|