KBaba7/llama.cpp
0
1#include "common.cuh"2 3void sum_rows_f32_cuda(const float * x, float * dst, const int ncols, const int nrows, cudaStream_t stream);4 5void ggml_cuda_op_sum_rows(ggml_backend_cuda_context & ctx, ggml_tensor * dst);6 1#include "common.cuh"2 3void sum_rows_f32_cuda(const float * x, float * dst, const int ncols, const int nrows, cudaStream_t stream);4 5void ggml_cuda_op_sum_rows(ggml_backend_cuda_context & ctx, ggml_tensor * dst);6