Context Window
概念
核心技术
The model's working memory — from 2K tokens to millions in five years.
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。
The context window is how much a model can consider at once. GPT-3 held 2K tokens; Gemini holds a million; long-context serving is why the KV cache (the stored state for every token in context) dominates inference memory and why chips like Rubin CPX exist just for the 'prefill' of huge contexts. Long context competes with retrieval (RAG) as the way to give models knowledge.
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。
来源
记录审阅截至 2026-01-15 — 查看 方法论.