llama.cpp 发布 b9632 版本：新增 Jinja count/d/e 过滤器别名并更新多平台构建
英文摘要
The llama.cpp project tagged release b9632. The primary change is the addition of count, d, and e filter aliases to the Jinja template engine via PR #24606. Pre-built binaries are published for a wide range of platforms: macOS arm64 with optional KleidiAI, Linux (CPU, Vulkan, ROCm 7.2, OpenVINO, SYCL FP32/FP16), Android arm64, and Windows (CPU, CUDA 12/13, Vulkan, SYCL, HIP). Several configurations are disabled in this release, including macOS Intel, iOS XCFramework, and openEuler 310p/910b builds.
中文摘要
llama.cpp 项目版本 b9632 发布。主要改动为通过 PR #24606 为 Jinja 模板引擎增加了 count、d 和 e 过滤器别名。该版本提供了大量平台的预编译二进制包，包括 macOS arm64（可选 KleidiAI）、Linux（CPU、Vulkan、ROCm 7.2、OpenVINO、SYCL FP32/FP16）、Android arm64 以及 Windows（CPU、CUDA 12/13、Vulkan、SYCL、HIP）。macOS Intel、iOS XCFramework 和 openEuler 310p/910b 等配置在本次发布中处于禁用状态。
关键要点
Added count, d, and e filter aliases to the Jinja template engine (PR #24606)
为 Jinja 模板引擎新增 count、d 和 e 过滤器别名（PR #24606）
Pre-built binaries cover macOS arm64 (KleidiAI enabled), Linux across CPU/Vulkan/ROCm/OpenVINO/SYCL backends, Android arm64, and Windows with CUDA/Vulkan/SYCL/HIP
预编译二进制覆盖 macOS arm64（启用 KleidiAI）、Linux（CPU/Vulkan/ROCm/OpenVINO/SYCL 后端）、Android arm64 和 Windows（CUDA/Vulkan/SYCL/HIP）
Disabled platform builds in this release include macOS Intel, iOS XCFramework, and openEuler configurations
本次发布中禁用了 macOS Intel、iOS XCFramework 和 openEuler 配置的构建