mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-09 10:11:44 +00:00
6 lines
213 B
Plaintext
6 lines
213 B
Plaintext
#include "common.cuh"
|
|
|
|
void sum_rows_f32_cuda(const float * x, float * dst, const int ncols, const int nrows, cudaStream_t stream);
|
|
|
|
void ggml_cuda_op_sum_rows(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|