跳到正文
Rohan Paul· @rohanpaul_ai · X·· 2026-05-25AI 评分47
AI 导读

Chamath谈AI计算中至关重要的“预填充”和“解码”。 预填充是计算密集型;大规模并行GPU胜出,因此随着上下文增长,Nvidia占据主导。 解码是内存带宽密集型,因为每个下一个token都依赖于扫描已生成的内容。

正文 · 原文

Chamath on all important “prefill” and “decode.” in AI compute.
Prefill is compute-bound; massive parallel GPUs win, so Nvidia dominates as context grows.
Decode is memory-bandwidth bound as each next token depends on scanning what’s already generated

来源:Rohan Paul · x.com