Inference
概念
训练与推理
Running the model — now the majority of AI compute and the focus of the buildout.
您正在查看一条概念解释记录：该术语的通俗含义，以及它所关联的各条目。
Inference is every ChatGPT answer, Copilot completion and API call — and as products scaled, it overtook training as the dominant AI workload. It splits into prefill (reading the prompt, compute-bound) and decode (generating tokens, memory-bandwidth-bound), which is why HBM decides serving economics, why engines like vLLM matter, and why hardware now specializes by phase (Rubin CPX). 'Tokens per dollar per watt' is the metric the whole industry is converging on.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
相关
来源
记录审阅截至 2026-01-15 — 查看 方法论.