ik-llama-cpp-sys 0.1.5

Low level bindings to ik_llama.cpp (ikawrakow's SOTA-quant fork)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12

//
// Copyright (C) 2024 Iwan Kawrakow
// MIT license
// SPDX-License-Identifier: MIT
//

#include "common.cuh"

struct mmvq_args;

void iqk_mul_mat_vec_q(ggml_type type, const mmvq_args & args, cudaStream_t stream);