llama.cpp releases
· Infrastructure
b10321
metal : fix NORM/RMS_NORM for row lengths that leave a partial simdgroup (#26708) ggml_metal_op_norm sized the threadgroup with nth = std::min(nth, args.ne00_t), which can leave nth not a multiple of the simdgroup size. The kernels finish their row reduction with a cross-simdgroup step where each lane of the last simdg