https://answer.freetools.me/tags/ttft/ Recent content in TTFT on Answer Hugo -- 0.152.2 zh-cn Wed, 11 Mar 2026 12:42:37 +0800 https://answer.freetools.me/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86%E4%B8%BA%E4%BB%80%E4%B9%88%E7%AC%AC%E4%B8%80%E4%B8%AA-token-%E6%80%BB%E6%98%AF%E5%BE%88%E6%85%A2%E4%BB%8E-prefill-%E5%88%B0-decode-%E7%9A%84%E5%AE%8C%E6%95%B4%E6%8A%80%E6%9C%AF%E8%A7%A3%E6%9E%90/ Wed, 11 Mar 2026 12:42:37 +0800 https://answer.freetools.me/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86%E4%B8%BA%E4%BB%80%E4%B9%88%E7%AC%AC%E4%B8%80%E4%B8%AA-token-%E6%80%BB%E6%98%AF%E5%BE%88%E6%85%A2%E4%BB%8E-prefill-%E5%88%B0-decode-%E7%9A%84%E5%AE%8C%E6%95%B4%E6%8A%80%E6%9C%AF%E8%A7%A3%E6%9E%90/ 深入解析大模型推理中 Prefill 与 Decode 两个阶段的本质差异。从计算强度、内存带宽瓶颈到 KV Cache 机制，揭示为什么首 Token 延迟与后续 Token 生成速度存在巨大差异，以及连续批处理、Chunked Prefill 等优化技术的原理。