ik-llama-cpp-sys 0.1.2

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
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

#pragma once

#include "ggml.h"

struct ggml_graph_node_properties {
    void * node_address;
    ggml_op node_op;
    int64_t ne[GGML_MAX_DIMS];
    size_t nb[GGML_MAX_DIMS];
    void * src_address[GGML_MAX_SRC];
    int32_t op_params[GGML_MAX_OP_PARAMS / sizeof(int32_t)];
};

struct ggml_cuda_graph {
#ifdef USE_CUDA_GRAPH
    ~ggml_cuda_graph() {
        if (instance != nullptr) {
            CUDA_CHECK(cudaGraphExecDestroy(instance));
        }
        if (graph != nullptr) {
            CUDA_CHECK(cudaGraphDestroy(graph));
        }
    }
    cudaGraph_t graph = nullptr;
    cudaGraphExec_t instance = nullptr;
    size_t num_nodes = 0;
    std::vector<cudaGraphNode_t> nodes;
    std::vector<cudaKernelNodeParams> params;
    bool disable_due_to_gpu_arch = false;
    bool disable_due_to_too_many_updates = false;
    bool disable_due_to_failed_graph_capture = false;
    int number_consecutive_updates = 0;
    std::vector<ggml_graph_node_properties> ggml_graph_properties;
    bool use_cpy_indirection = false;
    std::vector<char *> cpy_dest_ptrs;
    char ** dest_ptrs_d;
    int dest_ptrs_size = 0;
    // Index to allow each cpy kernel to be aware of it's position within the graph
    // relative to other cpy nodes.
    int graph_cpynode_index = -1;
#endif
};