fca2f948c1
### What this PR does / why we need it?
The test case `tests/e2e/multicard/test_data_parallel.py` was skipped
due to the errors encountered during migration from Ascend A2 to A3, the
details are as follows
```
(EngineCore_DP0 pid=17833) RuntimeError: npu_moe_distribute_dispatch_v2:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:161 NPU function error: call aclnnMoeDistributeDispatchV3 failed, error code is 561002
(EngineCore_DP0 pid=17833) [ERROR] 2025-12-23-07:36:19 (PID:17833, Device:0, RankID:-1) ERR00100 PTA call acl api failed.
(EngineCore_DP0 pid=17833) EZ9999: Inner Error!
(EngineCore_DP0 pid=17833) EZ9999[PID: 17833] 2025-12-23-07:36:19.237.396 (EZ9999): HCCL_BUFFSIZE is too SMALL, maxBs = 512, h = 2048, epWorldSize = 2, localMoeExpertNum = 64, sharedExpertNum = 0, tokenNeedSizeDispatch = 4608, tokenNeedSizeCombine = 4096, k = 8, NEEDED_HCCL_BUFFSIZE(((maxBs * tokenNeedSizeDispatch * ep_worldsize * localMoeExpertNum) + (maxBs * tokenNeedSizeCombine * (k + sharedExpertNum))) * 2) = 609MB, HCCL_BUFFSIZE=200MB.[FUNC:MoeDistributeDispatchA3TilingFuncImpl][FILE:moe_distribute_dispatch_v2_tiling.cc][LINE:941]
(EngineCore_DP0 pid=17833) TraceBack (most recent call last):
(EngineCore_DP0 pid=17833) MoeDistributeDispatchV2 do tiling failed, ret is -1.
(EngineCore_DP0 pid=17833) Check NnopbaseExecutorDoTiling(executor) failed
(EngineCore_DP0 pid=17833) Check NnopbaseExecutorTilingAndUpdateBinInfo(executor) failed
(EngineCore_DP0 pid=17833) Check NnopbaseExecutorMatchCache(executor) failed
(EngineCore_DP0 pid=17833) Check NnopbaseRunForWorkspace(*executor, workspaceSize) failed
```
### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
After fixed, I ran `pytest -sv --durations=0
tests/e2e/multicard/test_data_parallel.py`, and the result looks good
```
========================================================================================= warnings summary =========================================================================================
<frozen importlib._bootstrap>:241
<frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyPacked has no __module__ attribute
<frozen importlib._bootstrap>:241
<frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyObject has no __module__ attribute
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
======================================================================================== slowest durations =========================================================================================
112.69s call tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-vllm-ascend/Qwen3-30B-A3B-W8A8]
88.11s call tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-Qwen/Qwen3-30B-A3B]
70.06s call tests/e2e/multicard/test_data_parallel.py::test_qwen_inference_dp2[32-Qwen/Qwen3-0.6B]
(6 durations < 0.005s hidden. Use -vv to show these durations.)
============================================================================ 3 passed, 2 warnings in 270.88s (0:04:30) ============================================================================
```
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
Signed-off-by: wjunLu <wjunlu217@gmail.com>
82 lines
2.3 KiB
Python
82 lines
2.3 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.
|
|
#
|
|
"""
|
|
Compare the outputs of vLLM with and without aclgraph.
|
|
|
|
Run `pytest tests/multicard/test_data_parallel.py`.
|
|
"""
|
|
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
MODELS = [
|
|
"Qwen/Qwen3-0.6B", "Qwen/Qwen3-30B-A3B", "vllm-ascend/Qwen3-30B-A3B-W8A8"
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("max_tokens", [32])
|
|
@patch.dict(os.environ, {"ASCEND_RT_VISIBLE_DEVICES": "0,1"})
|
|
@patch.dict(os.environ, {"HCCL_BUFFSIZE": "1024"})
|
|
def test_qwen3_inference_dp2(model, max_tokens):
|
|
moe_models = ["Qwen/Qwen3-30B-A3B", "vllm-ascend/Qwen3-30B-A3B-W8A8"]
|
|
quantization_models = ["vllm-ascend/Qwen3-30B-A3B-W8A8"]
|
|
script = "examples/offline_data_parallel.py"
|
|
|
|
env = os.environ.copy()
|
|
|
|
cmd = [
|
|
sys.executable,
|
|
script,
|
|
"--model",
|
|
model,
|
|
"--dp-size",
|
|
"2",
|
|
"--tp-size",
|
|
"1",
|
|
"--node-size",
|
|
"1",
|
|
"--node-rank",
|
|
"0",
|
|
"--trust-remote-code",
|
|
]
|
|
|
|
if model in moe_models:
|
|
cmd.append("--enable-expert-parallel")
|
|
if model in quantization_models:
|
|
cmd.append("--quantization")
|
|
cmd.append("ascend")
|
|
|
|
print(f"Running subprocess: {' '.join(cmd)}")
|
|
proc = subprocess.run(cmd,
|
|
env=env,
|
|
stdout=subprocess.PIPE,
|
|
stderr=subprocess.STDOUT,
|
|
timeout=600)
|
|
output = proc.stdout.decode(errors='ignore')
|
|
|
|
print(output)
|
|
|
|
assert "DP rank 0 needs to process" in output
|
|
assert "DP rank 1 needs to process" in output
|
|
assert "Generated text:" in output
|
|
assert proc.returncode == 0
|