Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

attempt to debug

Browse Source
This commit is contained in:
Concedo
2025-05-31 01:02:30 +08:00
parent 6529326c59
commit 3829ae728e
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn-mma-f16.cuh
+2 -1
View File
@@ -1243,10 +1243,11 @@ static __global__ void flash_attn_ext_f16(
}
#if __CUDA_ARCH__ == GGML_CUDA_CC_TURING
if (ncols1*ncols2 > 32) {
printf("\nCUDA_ARCH:%d, DKQ:%d, DV:%d, ncols1:%d, ncols2:%d, nwarps:%d, ntiles:%d, ne00:%d, ne01:%d\n",__CUDA_ARCH__,DKQ, DV, ncols1, ncols2, nwarps, ntiles,ne00,ne01);
NO_DEVICE_CODE;
return;
}
#endif __CUDA_ARCH__ == GGML_CUDA_CC_TURING
#endif // __CUDA_ARCH__ == GGML_CUDA_CC_TURING
static_assert(!mla || DKQ >= DV, "MLA needs DKQ >= DV");