llama.cpp 发布: b11114

来源摘要

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 dying child. Such a request now joins the queue and is served by the next instance. The stopping mark is cleared under the same lock that sets UNLOADED, so no request can see a model that is neither stopping nor unloaded while its child is gone. **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11114/llama-b11114-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11114/llama-b11114-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11114/llama-b11114-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11114/llama-b11114-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11114/llama-b11114-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11114/llama-b11114-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11114/llama-b11114-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github