13cd6362c6
### What this PR does / why we need it?
When matmul_and_reduce is enabled, the prefix attribute is required.
However, in some models, the prefix is not passed correctly, causing
errors when starting the service.
The issue of incorrect prefix passing will be fixed in vLLM in the
future.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
# Adapted from vllm/tests/entrypoints/llm/test_guided_generate.py
|
|
# 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.
|
|
#
|
|
|
|
import os
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
|
|
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
|
|
|
|
|
|
def test_minicpm_2b() -> None:
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
max_tokens = 5
|
|
|
|
with VllmRunner("openbmb/MiniCPM-2B-sft-bf16",
|
|
max_model_len=512,
|
|
gpu_memory_utilization=0.7) as runner:
|
|
runner.generate_greedy(example_prompts, max_tokens)
|