llama-cpp-sys-4 0.9.0

Low Level Bindings to llama.cpp
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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92

#include "llama-memory.h"

#include "llama-ext.h"
#include "llama-io.h"

#include <set>
#include <vector>

llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_memory_status s1) {
    bool has_update = false;

    switch (s0) {
        case LLAMA_MEMORY_STATUS_SUCCESS:
            {
                has_update = true;
                break;
            }
        case LLAMA_MEMORY_STATUS_NO_UPDATE:
            {
                break;
            }
        case LLAMA_MEMORY_STATUS_FAILED_PREPARE:
        case LLAMA_MEMORY_STATUS_FAILED_COMPUTE:
            {
                return s0;
            }
    }

    switch (s1) {
        case LLAMA_MEMORY_STATUS_SUCCESS:
            {
                has_update = true;
                break;
            }
        case LLAMA_MEMORY_STATUS_NO_UPDATE:
            {
                break;
            }
        case LLAMA_MEMORY_STATUS_FAILED_PREPARE:
        case LLAMA_MEMORY_STATUS_FAILED_COMPUTE:
            {
                return s1;
            }
    }

    // if either status has an update, then the combined status has an update
    return has_update ? LLAMA_MEMORY_STATUS_SUCCESS : LLAMA_MEMORY_STATUS_NO_UPDATE;
}

bool llama_memory_status_is_fail(llama_memory_status status) {
    switch (status) {
        case LLAMA_MEMORY_STATUS_SUCCESS:
        case LLAMA_MEMORY_STATUS_NO_UPDATE:
            {
                return false;
            }
        case LLAMA_MEMORY_STATUS_FAILED_PREPARE:
        case LLAMA_MEMORY_STATUS_FAILED_COMPUTE:
            {
                return true;
            }
    }

    return false;
}

// collects the buffers of the tensors that a state write visits, without keeping the data
struct llama_memory_buffers_writer : public llama_io_write_i {
    std::set<ggml_backend_buffer_t> buffers;
    size_t size = 0;

    void write(const void *, size_t n) override {
        size += n;
    }

    void write_tensor(ggml_tensor * tensor, size_t, size_t n) override {
        buffers.insert(tensor->buffer);
        size += n;
    }

    size_t n_bytes() override {
        return size;
    }
};

std::vector<ggml_backend_buffer_t> llama_memory_get_buffers(const llama_memory_t mem) {
    llama_memory_buffers_writer writer;

    mem->state_write(writer);

    return std::vector<ggml_backend_buffer_t>(writer.buffers.begin(), writer.buffers.end());
}