diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp index 761b7f9c664d..b51214360feb 100644 --- a/ggml/src/ggml-sycl/ggml-sycl.cpp +++ b/ggml/src/ggml-sycl/ggml-sycl.cpp @@ -3540,6 +3540,7 @@ static void ggml_sycl_mul_mat_batched_sycl(ggml_backend_sycl_context & ctx, cons " : converting src1 to fp16"); #if GGML_SYCL_DNNL + if (g_ggml_sycl_enable_dnn) { // iterate tensor dims and find the slowest moving dim and stride int last_dim=0; int last_str=0; @@ -3565,13 +3566,15 @@ static void ggml_sycl_mul_mat_batched_sycl(ggml_backend_sycl_context & ctx, cons const to_fp16_sycl_t to_fp16_sycl = ggml_get_to_fp16_sycl(src1->type, dst); GGML_ASSERT(to_fp16_sycl != nullptr); to_fp16_sycl(src1_f16, src1_f16_alloc.get(), ne_src1, queue); -# else + } else +#endif + { const int64_t ne_src1 = ggml_nelements(src1); src1_f16_alloc.alloc(ne_src1); const to_fp16_nc_sycl_t to_fp16_nc_sycl = ggml_get_to_fp16_nc_sycl(src1->type); GGML_ASSERT(to_fp16_nc_sycl != nullptr); to_fp16_nc_sycl(src1_f16, src1_f16_alloc.get(), ne10, ne11, ne12, ne13, s11, s12, s13, queue); -#endif + } src1_f16 = src1_f16_alloc.get(); s11 = ne10;