ik-llama-cpp-sys 0.1.3

Low level bindings to ik_llama.cpp (ikawrakow's SOTA-quant fork)
Documentation 
1
2
3
4
5
6
7
8
9

#include "common.cuh"

void ggml_cuda_op_sum_rows(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

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_div(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_sum_rows_nc(ggml_backend_cuda_context & ctx, ggml_tensor * dst);