PyPI page
Home page
Author:
vLLM Team
License:
Apache 2.0
Summary:
A high-throughput and memory-efficient inference and serving engine for LLMs
Latest version:
0.4.2
Required dependencies:
cmake
|
fastapi
|
filelock
|
lm-format-enforcer
|
ninja
|
numpy
|
nvidia-ml-py
|
openai
|
outlines
|
prometheus-client
|
prometheus-fastapi-instrumentator
|
psutil
|
py-cpuinfo
|
pydantic
|
ray
|
requests
|
sentencepiece
|
tiktoken
|
tokenizers
|
torch
|
transformers
|
typing-extensions
|
uvicorn
|
vllm-nccl-cu12
|
xformers
Optional dependencies:
tensorizer
Downloads last day:
15,842
Downloads last week:
98,601
Downloads last month:
507,194