llama.cpp Release b9628 Adds SYCL Backend to CI Testing Pipeline
English summary
The b9628 release of llama.cpp integrates SYCL backend validation into the continuous integration and release testing pipeline. The new check-release workflow now covers SYCL FP32 and FP16 builds on Ubuntu x64 and SYCL on Windows x64, ensuring Intel GPU acceleration is regularly tested. The release also maintains existing test matrices for macOS, Linux (CPU, Vulkan, ROCm, OpenVINO), Android, and Windows (CUDA, Vulkan, HIP).
Chinese summary
llama.cpp 的 b9628 版本将 SYCL 后端的验证纳入持续集成和发布测试流程。新增的 check-release 工作流现覆盖 Ubuntu x64 上的 SYCL FP32 与 FP16 构建以及 Windows x64 上的 SYCL,确保英特尔 GPU 加速获得定期测试。该版本同时保留了针对 macOS、Linux(CPU、Vulkan、ROCm、OpenVINO)、Android 及 Windows(CUDA、Vulkan、HIP)的现有测试矩阵。
Key points
Added SYCL backend (FP32 and FP16) testing for Ubuntu and Windows to the release pipeline.
将 SYCL 后端(FP32 和 FP16)的测试加入 Ubuntu 和 Windows 的发布流水线。
Enables validated builds for Intel GPU inference via the SYCL API.
通过 SYCL API 实现经过验证的英特尔 GPU 推理构建。
Release maintains broad platform coverage including CPU, CUDA, Vulkan, ROCm, OpenVINO, and HIP backends.
该版本保持了对多种平台的覆盖,包括 CPU、CUDA、Vulkan、ROCm、OpenVINO 和 HIP 后端。