ik-llama-cpp-sys 0.1.4

Low level bindings to ik_llama.cpp (ikawrakow's SOTA-quant fork)
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);