llama.cpp PR reports up to 169% faster quantized-KV decode at 118K context on Intel Battlemage from one SYCL kernel switch

A fresh llama.cpp PR (#26689) changes what looks like a tiny SYCL FlashAttention dispatch decision. With a quantized KV cache ("q4_0" / "q8_0"), decode was being sent through the VEC kernel. On the author's Battlemage test system, switching that path to TILE gets much faster as context grows. Some o