increase cuda_cpy block size (#996)

Co-authored-by: bssrdf <redacted>

diff --git a/src/ggml-cuda/cpy.cuh b/src/ggml-cuda/cpy.cuh
index 7961674266ee1c67d69ab4077b84646d5e61009d..28b06cddaa87b98316ae3a94fe3ff793812d398b 100644 (file)
--- a/src/ggml-cuda/cpy.cuh
+++ b/src/ggml-cuda/cpy.cuh
@@ -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);