llama.cpp b9624 adds UI build-time gzip compression and fixes filename handling
English summary
Release b9624 of llama.cpp introduces build-time gzip compression for the web UI and resolves a nocache issue to preserve original file names and paths. Pre-built binaries are provided for macOS (Apple Silicon with KleidiAI disabled, Intel x64), Linux (multiple CPU and GPU backends), Windows (CPU, CUDA 12/13, Vulkan, SYCL, HIP), Android arm64, and openEuler platforms. This release also extends CI coverage across many configurations.
Chinese summary
llama.cpp b9624 版本为 Web UI 引入了构建时 gzip 压缩，并修复了 nocache 问题以保留原始文件名和路径。发布了适用于 macOS（Apple Silicon 上 KleidiAI 被禁用，Intel x64）、Linux（多种 CPU 和 GPU 后端）、Windows（CPU、CUDA 12/13、Vulkan、SYCL、HIP）、Android arm64 及 openEuler 平台的预编译二进制文件。该版本还扩展了多个配置的持续集成覆盖范围。
Key points
Web UI now supports build-time gzip compression for reduced payload sizes.
Web UI 现在支持构建时 gzip 压缩以减少有效载荷大小。
Fixed nocache issue to keep original file name and path in the UI.
修复了 nocache 问题，使 UI 能够保留原始文件名和路径。
Pre-built binaries cover a wide range of platforms including macOS arm64 with KleidiAI disabled.
预编译二进制文件覆盖广泛平台，包括 macOS arm64（KleidiAI 已禁用）。
Release extends CI to many Linux, Windows, and openEuler configurations.
该版本将持续集成扩展到许多 Linux、Windows 和 openEuler 配置。