llama.cpp b11815：修复 SYCL 后端 CONV_2D 非连续输入错误
原标题：b11815
AI 摘要
llama.cpp 发布 b11815 版本，主要修复 SYCL 后端 CONV_2D 算子在非连续输入下因按连续 [W,H,C,N] 布局索引而静默产生错误结果的问题，通过按 CUDA 后端约定对 input 与 kernel 的连续性做门控并断言。同时为 SYCL 后端新增 CWHN 通道顺序布局的 CONV_2D 计算支持，使相关 test-backend-ops 用例从 16 个失败变为全部通过。该版本还同步更新了 SYCL 算子文档，并提供 macOS、Linux、Android、Windows 各平台多种后端（CPU、CUDA、Vulkan、ROCm、SYCL、OpenVINO 等）的预编译包。
正文节选
<details open> sycl: fix CONV_2D wrong results for non-contiguous input (#30363) * sycl: fix CONV_2D wrong results for non-contiguous input The kernel indexes the `input` as a contiguous [W, H, C, N] tensor, but supports_op claimed the op for any layout. A non-contiguous (e.g. `CWHN` permuted) input was read with the wrong element offsets, silently producing wrong results. Gate the CONV_2D op on `input` and `kernel` contiguity, matching the CUDA backend contract, and assert input contiguity