/speculative-decoding
用 speculative decoding、Medusa 多頭與 lookahead decoding 加速 LLM 推論。最佳化推論速度、降低即時應用的延遲，或在有限算力下部署模型時使用。
- 安裝次數
- 983
- 專案星數
- 1.4 萬 ★
- 授權
- MIT
- 專案更新
- 2026-10-11
怎麼裝
npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs --skill speculative-decoding安裝前請先看過原文內容。中文說明是 AI 翻譯，不保證安全。
原文
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.