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 with GGML_CUDA_F16 (#14837)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-07-23 18:22:30 +02:00
committed by GitHub
parent 221c0e0c58
commit b284197df4
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/convert.cu
View File

@@ -31,8 +31,8 @@ static __global__ void dequantize_block(const void * __restrict__ vx, dst_t * __
dequantize_kernel(vx, ib, iqs, v); dequantize_kernel(vx, ib, iqs, v);
const int64_t iy0 = ((i03*ne02 + i02)*ne01 + i01)*ne00 + iybs + iqs; const int64_t iy0 = ((i03*ne02 + i02)*ne01 + i01)*ne00 + iybs + iqs;
y[iy0 + 0] = v.x; y[iy0 + 0] = float(v.x);
y[iy0 + y_offset] = v.y; y[iy0 + y_offset] = float(v.y);
} }
template <bool need_check> template <bool need_check>