🐼 mlops

👇 2 Éléments

vllm

33.9k Python Apache-2.0

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

1 il y a 2 an(s) il y a 1 moi(s)

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 il y a 6 moi(s) il y a 19 jour(s)