llama.cpp b11243：升级 oneAPI 2026.1，SYCL 提示处理提速 3.1 倍
原标题：b11243
AI 摘要
llama.cpp 发布 b11243 版本，主要更新 CI 与构建流程以适配 Intel oneAPI 2026.1 工具包。由于 oneDNN 在 2026.0 起从 Intel Deep Learning Essentials 中移除，项目将 Ubuntu 和 Windows CI 切换到统一的 oneAPI Toolkit 安装器以保留 oneDNN 支持。在 Arc B570 上实测，使用 oneAPI 2026.1 构建后提示处理速度从 434 t/s 提升至 1331 t/s（约 3.1 倍），token 生成速度也有小幅提升。
正文节选
<details open> ci : update the oneAPI toolkit to 2026.1 (#29273) * ci : update the oneAPI toolkit to 2026.1 oneDNN is removed from Intel Deep Learning Essentials in 2026.0, so staying on the deep-learning-essentials path would silently lose oneDNN support when the toolkit version is updated. Switch both the Ubuntu and Windows CI jobs to the new unified Intel oneAPI Toolkit installer, which still includes oneDNN (until 2027.0) and keeps the component IDs unchanged for the Windows install scrip