e1ab6d318e
More and more config options are added to additional_config. This PR provide a new AscendConfig to manage these config options by an easier way to make code cleaner and readable. This PR also added the `additional_config` doc for users. Added the test_ascend_config.py to make sure the new AscendConfig works as expect. TODO: Add e2e test with torchair and deepseek once the CI resource is available. Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
60 lines
1.8 KiB
Python
60 lines
1.8 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/test_offline_inference.py`.
|
|
"""
|
|
import os
|
|
|
|
import vllm # noqa: F401
|
|
|
|
from tests.conftest import VllmRunner
|
|
|
|
os.environ["PYTORCH_NPU_ALLOC_CONF"] = "max_split_size_mb:256"
|
|
|
|
|
|
def test_models_distributed_QwQ():
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
dtype = "half"
|
|
max_tokens = 5
|
|
with VllmRunner(
|
|
"Qwen/QwQ-32B",
|
|
dtype=dtype,
|
|
tensor_parallel_size=4,
|
|
distributed_executor_backend="mp",
|
|
) as vllm_model:
|
|
vllm_model.generate_greedy(example_prompts, max_tokens)
|
|
|
|
|
|
def test_models_distributed_DeepSeek():
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
dtype = "half"
|
|
max_tokens = 5
|
|
with VllmRunner(
|
|
"deepseek-ai/DeepSeek-V2-Lite",
|
|
dtype=dtype,
|
|
tensor_parallel_size=4,
|
|
distributed_executor_backend="mp",
|
|
) as vllm_model:
|
|
vllm_model.generate_greedy(example_prompts, max_tokens)
|