llama.cpp b11552 修复忙槽位被 prompt cache 覆盖问题

AI 摘要

llama.cpp 发布 b11552 版本，修复了服务器端一个并发调度缺陷：当某个请求指定了正被占用的 id_slot 时，此前仍会先对该槽位执行 prompt cache 更新，导致在另一请求仍在生成时把更匹配的缓存载入该槽位，使生成在错误的上下文上继续。现在该忙槽位会被原样返回，请求需等待其释放。

正文节选

<details open> server: leave a busy slot untouched when a request pins it (#30295) A request asking for a busy id_slot still ran the prompt cache update on that slot before being deferred. When the RAM cache held a better match, it was loaded into the slot while another request was still generating there, and that generation continued on the wrong context. The busy slot is now returned as is and the request waits for it. </details> **Website:** - <https://llama.app> **Attestations:** - <ht

发布时间：2026-10-11 03:52

抓取时间：2026-10-11 04:16

来源机构：ggml-org