20260514:增加新内容

This commit is contained in:
2026-05-14 13:54:52 +08:00
parent 56c4d3ef7c
commit b116710e4c
294 changed files with 10682 additions and 255 deletions

View File

@@ -1,3 +1,12 @@
---
title: KV 缓存内存瓶颈
created: 2025-04-15
updated: 2026-05-01
type: concept
tags: []
sources: []
---
# KV 缓存内存瓶颈
**自回归推理中的核心内存瓶颈**KV 缓存的线性增长严重限制 LLM 推理效率。