CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix compilation on CC 6.0 (#16091)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-09-18 19:28:32 +02:00
committed by GitHub
parent 4ca088b036
commit 368560a1e3
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn-tile.cu
View File

@@ -35,7 +35,6 @@ static int fattn_tile_get_kq_stride_host(const int D, const int ncols, const int
switch (D) { switch (D) {
case 64: case 64:
case 128: case 128:
return 128;
case 256: case 256:
return ncols <= 16 ? 128 : 64; return ncols <= 16 ? 128 : 64;
default: default:
@@ -86,7 +85,6 @@ static constexpr __device__ int fattn_tile_get_kq_stride_device(int D, int ncols
switch (D) { switch (D) {
case 64: case 64:
case 128: case 128:
return 128;
case 256: case 256:
return ncols <= 16 ? 128 : 64; return ncols <= 16 ? 128 : 64;
default: default: