diff --git a/ggml/src/ggml-sycl/dmmv.cpp b/ggml/src/ggml-sycl/dmmv.cpp index 5c343822f..0c3dfaa37 100644 --- a/ggml/src/ggml-sycl/dmmv.cpp +++ b/ggml/src/ggml-sycl/dmmv.cpp @@ -76,8 +76,8 @@ static void dequantize_mul_mat_vec(const void * __restrict__ vx, const dfloat * } // sum up partial sums and write back result -#pragma unroll - for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) { + const int mask_start = ncols > GGML_SYCL_DMMV_X ? WARP_SIZE >> 1 : WARP_SIZE >> 2; + for (int mask = mask_start; mask > 0; mask >>= 1) { tmp += dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask); }