llama.cpp b11756：Anthropic /v1/messages 透传 id_slot

AI 摘要

llama.cpp 发布 b11756 版本，修复了 server 端在 Anthropic /v1/messages 接口转换过程中未透传 id_slot 参数的问题。此前该接口会忽略 id_slot，导致依赖固定 slot 复用 KV cache 的代理回退到自动 slot 选择，在混合/循环模型上触发完整重新 prefill。该改动使 /v1/messages 与其他补全端点行为一致，并同步提供各平台预编译二进制。

正文节选

<details open> server : pass id_slot through the Anthropic /v1/messages conversion (#28554) * server : pass id_slot through the Anthropic /v1/messages conversion server_chat_convert_anthropic_to_oai copies a small whitelist of common params from the Anthropic request into the internal OAI-style body and left id_slot out. Every other completion endpoint honours id_slot; a proxy that pins a session to the slot holding its KV cache needs the same on /v1/messages, or it silently falls back to aut

发布时间：2026-10-20 21:48

抓取时间：2026-10-20 22:25

来源机构：ggml-org