increase cuda_cpy block size (ggml/996)

Co-authored-by: bssrdf <[email protected]>
l3utterfly · Oct 26, 2024 · 8c60a8a · 8c60a8a
1 parent 9e4a256
commit 8c60a8a
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/ggml/src/ggml-cuda/cpy.cuh b/ggml/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);