🐼 mlops

👇 2 个项目

vllm

33.9k Python Apache-2.0

A high-throughput and memory-efficient inference and serving engine for LLMs

1 2 年前 1 个月前

scuda

1.6k C++ Apache-2.0

SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

1 6 个月前 19 天前