Co-authored-by: bssrdf <bssrdf@gmail.com>
@@ -1,6 +1,6 @@
#include "common.cuh"
-#define CUDA_CPY_BLOCK_SIZE 32
+#define CUDA_CPY_BLOCK_SIZE 64
void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, ggml_tensor * src1);