LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, supporting hybrid inference for MOE large models.
This repository is tracked by Trending Repos. The badge upgrades automatically the moment it cracks the top 100 — set it once and forget it.
[](https://trending-repos.com/repositories/guqiong96/Lvllm)<a href="https://trending-repos.com/repositories/guqiong96/Lvllm"><img src="https://trending-repos.com/badge/guqiong96/Lvllm.svg" alt="Trending Repos" /></a>https://trending-repos.com/badge/guqiong96/Lvllm.svg