llama-cpp-sys-4 0.2.45

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7

#pragma once

#include "common.cuh"

#define CUDA_SET_ROWS_BLOCK_SIZE 256

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