LangChain

还没翻译译自英文（docs.vllm.ai）本页 6 段都还没译

LangChain

vLLM is also available via LangChain .

To install LangChain, run

pip install langchain langchain_community -q

To run inference on a single or multiple GPUs, use VLLM class from langchain.

from langchain_community.llms import VLLM

llm = VLLM(
    model="Qwen/Qwen3-4B",
    trust_remote_code=True,  # mandatory for hf models
    max_new_tokens=128,
    top_k=10,
    top_p=0.95,
    temperature=0.8,
    # for distributed inference
    # tensor_parallel_size=...,
)

print(llm("What is the capital of France ?"))

Code

from langchain_community.llms import VLLM

llm = VLLM(
    model="Qwen/Qwen3-4B",
    trust_remote_code=True,  # mandatory for hf models
    max_new_tokens=128,
    top_k=10,
    top_p=0.95,
    temperature=0.8,
    # for distributed inference
    # tensor_parallel_size=...,
)

print(llm("What is the capital of France ?"))

Please refer to this Tutorial for more details.

Edit on GitHub

AI 翻译查看英文原文