46 lines
1.5 KiB
Python
46 lines
1.5 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-project/vllm/examples/offline_inference/basic.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.
|
||
|
|
#
|
||
|
|
|
||
|
|
from vllm import LLM, SamplingParams
|
||
|
|
|
||
|
|
prompts = [
|
||
|
|
"Hello, my name is",
|
||
|
|
"The president of the United States is",
|
||
|
|
"The capital of France is",
|
||
|
|
"The future of AI is",
|
||
|
|
]
|
||
|
|
|
||
|
|
# Create a sampling params object.
|
||
|
|
sampling_params = SamplingParams(max_tokens=100, temperature=0.0)
|
||
|
|
# Create an LLM.
|
||
|
|
# TODO (cmq): ray is not supported currently, need some fixes
|
||
|
|
llm = LLM(
|
||
|
|
model="facebook/opt-125m",
|
||
|
|
tensor_parallel_size=2,
|
||
|
|
distributed_executor_backend="mp",
|
||
|
|
trust_remote_code=True,
|
||
|
|
)
|
||
|
|
|
||
|
|
# Generate texts from the prompts.
|
||
|
|
outputs = llm.generate(prompts, sampling_params)
|
||
|
|
for output in outputs:
|
||
|
|
prompt = output.prompt
|
||
|
|
generated_text = output.outputs[0].text
|
||
|
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|