llama.cpp b11642：server 仅缓存可恢复的 slot 状态
原标题：b11642
AI 摘要
llama.cpp 发布 b11642 版本，主要改进 server 端的 prompt cache 机制：现在只保存可恢复的 slot 状态到缓存中，避免 rerank、embedding、decision、infill 等任务的状态无意义地占满缓存。改动引入 cache_pending 标记跟踪可恢复状态，并让 infill 和 decision 任务也能从缓存恢复；decision 模型默认禁用 prompt cache，除非显式指定 --cache-ram。同时发布了覆盖 macOS、Linux、Windows、Android 的多平台预编译二进制包。
正文节选
<details open> server: save only restorable slot states to the prompt cache (#30498) * server: save only restorable slot states to the prompt cache The idle-slot save loop stores every idle slot whenever a task starts, while only completion tasks restore from the prompt cache. Rerank, embedding, decision and infill states fill the cache up to its limit without ever being read back, and slots already cached are offered again at every task start. Each slot now tracks with cache_pending whether