* fix win build conflict of math library * fix the condition: !(win32 & SYCL) * revert warp_size=16
* use warp_size macro for all sycl kernels * fix mask of permute_sub_group_by_xor * fix rms_norm with correct warp number * fix rms_norm_f32/group_norm_f32 * move norm to norm.cpp file * fix quantize bug * fix mmvq's batch size
* add sycl preset * fix debug link error. fix windows crash * update README