~ / skills / research / speculative-decoding

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing…

Industry: research
License: Unverified
Source repo: Orchestra-Research/AI-Research-SKILLs · ★ 10,718
Source file: 19-emerging-techniques/speculative-decoding/SKILL.md

View full SKILL.md on GitHub →

不会安装？看中文图文教程 →