tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

64bit multiplication [no ci]

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-06-13 17:11:01 +02:00
committed by Akarshan
parent 70e8b48e6a
commit f8705a2399
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/unary.cu
View File

@ -200,7 +200,7 @@ void ggml_cuda_op_log(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
template <float (*op)(float), typename T> template <float (*op)(float), typename T>
static __global__ void unary_gated_op_kernel(const T * x, T * dst, const int64_t k, const int64_t n, const int64_t o) { static __global__ void unary_gated_op_kernel(const T * x, T * dst, const int64_t k, const int64_t n, const int64_t o) {
const int64_t i = blockDim.x*blockIdx.x + threadIdx.x; const int64_t i = int64_t(blockDim.x)*blockIdx.x + threadIdx.x;
if (i >= k) { if (i >= k) {
return; return;