CUDA: General GEMV fusion (#16715)

2025-10-26 19:28:04 +08:00
parent 3cfa9c3f12
commit f77c13b91f
11 changed files with 1096 additions and 166 deletions
--- a/ggml/src/ggml-cuda/convert.cuh
+++ b/ggml/src/ggml-cuda/convert.cuh
@@ -1,3 +1,4 @@
+#pragma once
 #include "common.cuh"

 #define CUDA_DEQUANTIZE_BLOCK_SIZE 256