vLLM 0.9 Optimization: Chunked Prefill, Speculative, FP8 KV Cache

Este artigo está publicado em japonês. Resumo em português abaixo:

vLLM 0.9 Optimization: Chunked Prefill, Speculative, FP8 KV Cache—vLLM 0.9 optimization tricks measured: chunked prefill, speculative decoding, FP8 KV cache and prefix caching, quantified on Llama and Qwen workloads in internal R&D.