d9cdc65854
### What this PR does / why we need it? Upgrade to new vllm commit:c9461e05a4- Fix many imports, caused by https://github.com/vllm-project/vllm/pull/26908 - Fix import ```sha256```, caused by https://github.com/vllm-project/vllm/pull/27169 - Remove ```SchedulerConfig.send_delta_data```, caused by https://github.com/vllm-project/vllm/pull/27142 - Fix ```FusedMoE``` because of dual stream execution, caused by https://github.com/vllm-project/vllm/pull/26440 ### Does this PR introduce _any_ user-facing change? N/A ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.11.0rc3 - vLLM main:17c540a993--------- Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: Icey <1790571317@qq.com> Co-authored-by: MengqingCao <cmq0113@163.com>
105 lines
3.2 KiB
Python
105 lines
3.2 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.
|
|
#
|
|
from typing import Any
|
|
|
|
import openai
|
|
import pytest
|
|
|
|
from tests.e2e.conftest import RemoteOpenAIServer
|
|
from tools.aisbench import run_aisbench_cases
|
|
from vllm_ascend.utils import vllm_version_is
|
|
|
|
if vllm_version_is("0.11.0"):
|
|
from vllm.utils import get_open_port
|
|
else:
|
|
from vllm.utils.network_utils import get_open_port
|
|
|
|
MODELS = [
|
|
"Qwen/Qwen3-32B",
|
|
]
|
|
|
|
TENSOR_PARALLELS = [4]
|
|
|
|
prompts = [
|
|
"San Francisco is a",
|
|
]
|
|
|
|
api_keyword_args = {
|
|
"max_tokens": 10,
|
|
}
|
|
|
|
aisbench_cases = [{
|
|
"case_type": "accuracy",
|
|
"dataset_path": "vllm-ascend/gsm8k-lite",
|
|
"request_conf": "vllm_api_general_chat",
|
|
"dataset_conf": "gsm8k/gsm8k_gen_0_shot_cot_chat_prompt",
|
|
"max_out_len": 32768,
|
|
"batch_size": 32,
|
|
"baseline": 95,
|
|
"threshold": 5
|
|
}, {
|
|
"case_type": "performance",
|
|
"dataset_path": "vllm-ascend/GSM8K-in3500-bs400",
|
|
"request_conf": "vllm_api_stream_chat",
|
|
"dataset_conf": "gsm8k/gsm8k_gen_0_shot_cot_str_perf",
|
|
"num_prompts": 80,
|
|
"max_out_len": 1500,
|
|
"batch_size": 20,
|
|
"request_rate": 0,
|
|
"baseline": 1,
|
|
"threshold": 0.97
|
|
}]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("tp_size", TENSOR_PARALLELS)
|
|
async def test_models(model: str, tp_size: int) -> None:
|
|
port = get_open_port()
|
|
env_dict = {
|
|
"TASK_QUEUE_ENABLE": "1",
|
|
"OMP_PROC_BIND": "false",
|
|
"HCCL_OP_EXPANSION_MODE": "AIV",
|
|
"PAGED_ATTENTION_MASK_LEN": "5500"
|
|
}
|
|
server_args = [
|
|
"--no-enable-prefix-caching", "--tensor-parallel-size",
|
|
str(tp_size), "--port",
|
|
str(port), "--max-model-len", "36864", "--max-num-batched-tokens",
|
|
"36864", "--block-size", "128", "--trust-remote-code",
|
|
"--gpu-memory-utilization", "0.9", "--additional-config",
|
|
'{"enable_weight_nz_layout":true}'
|
|
]
|
|
request_keyword_args: dict[str, Any] = {
|
|
**api_keyword_args,
|
|
}
|
|
with RemoteOpenAIServer(model,
|
|
server_args,
|
|
server_port=port,
|
|
env_dict=env_dict,
|
|
auto_port=False) as server:
|
|
client = server.get_async_client()
|
|
batch = await client.completions.create(
|
|
model=model,
|
|
prompt=prompts,
|
|
**request_keyword_args,
|
|
)
|
|
choices: list[openai.types.CompletionChoice] = batch.choices
|
|
assert choices[0].text, "empty response"
|
|
# aisbench test
|
|
run_aisbench_cases(model, port, aisbench_cases)
|