←back to thread

Nano-Vllm: Lightweight vLLM implementation built from scratch

(github.com)
124 points simonpure | 1 comments | 23 Jun 25 05:10 UTC | HN request time: 0.312s | source
1. futurecliff ◴[23 Jun 25 11:14 UTC] No.44354480[source]▶
how did u do it? which portion of vllm refactoring allowed u to get such gains.