llama.cpp Release b9655 Fixes Long-standing Grammar Generator Bug in Chat
English summary
The llama.cpp project released tag b9655, which fixes an 'oldie but goodie' grammar generator bug in the chat feature that surfaced during recent changes (PR #24653). Additionally, an erroneous case in the PEG parser test was updated. The release provides pre-built binaries for a wide range of platforms including macOS (Apple Silicon, Intel, KleidiAI), Linux (x64, arm64, s390x, Vulkan, ROCm, OpenVINO, SYCL), Android (arm64), and Windows (x64, arm64, CUDA 12/13, Vulkan, SYCL, HIP). openEuler builds and UI components are also included.
Chinese summary
llama.cpp 项目发布标签 b9655，修复了聊天功能中因近期代码变动而暴露的一个“古老但经典的”语法生成器 bug（PR #24653），并更新了 PEG 解析器测试中的一个错误用例。该版本提供了面向广泛平台的预编译二进制文件，包括 macOS（Apple Silicon、Intel、KleidiAI）、Linux（x64、arm64、s390x、Vulkan、ROCm、OpenVINO、SYCL）、Android（arm64）以及 Windows（x64、arm64、CUDA 12/13、Vulkan、SYCL、HIP），同时也包含了 openEuler 构建版本和 UI 组件。
Key points
Fixes an old grammar generator bug in the chat feature that became apparent after recent code changes (PR #24653).
修复了聊天功能中因近期代码变更而显现的一个旧有语法生成器 bug（PR #24653）。
Release includes pre-built binaries for macOS, Linux, Windows, and Android with various acceleration backends (Vulkan, CUDA, ROCm, OpenVINO, SYCL).
发布包含面向 macOS、Linux、Windows、Android 的预编译二进制文件，并支持 Vulkan、CUDA、ROCm、OpenVINO、SYCL 等多种加速后端。