llama.cpp b11114：修复 server 路由驱逐竞态

AI 摘要

llama.cpp 发布 b11114 版本，主要修复了 server 端路由驱逐（eviction）与现有队列之间的竞态问题。改动包括：所有模型加载都经过队列，使队列条目在等待者离开前保护模型不被 tick() 驱逐；同时不再将请求放入正在停止的模型，而是让其加入队列由下一个实例处理。该版本还提供了 macOS、Linux、Windows、Android 等多平台预编译二进制。

正文节选

<details open> server: fix router eviction races with the existing queue (#29217) * server: route every model load through the queue A model loaded by the fast path has no queue entry, so tick() evicts it at its LOADED transition before its own request is proxied. Every load now joins the queue, whose entry protects the model until its waiters leave. * server: do not admit requests into a stopping model A request for a model that is being stopped still sees it LOADED and is proxied into the

发布时间：2026-09-23 05:11

抓取时间：2026-09-23 05:37

来源机构：ggml-org