File size: 5,224 Bytes
57e3690
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
#include "ggml-cpu.h"

#ifdef GGML_USE_CUDA
#include "ggml-cuda.h"
#endif

#ifdef GGML_USE_METAL
#include "ggml-metal.h"
#endif

#ifdef GGML_USE_VULKAN
#include "ggml-vulkan.h"
#endif

#include "ggml-rpc.h"
#ifdef _WIN32
#  include <windows.h>
#else
#  include <unistd.h>
#endif
#include <string>
#include <stdio.h>

struct rpc_server_params {
    std::string host        = "127.0.0.1";
    int         port        = 50052;
    size_t      backend_mem = 0;
};

static void print_usage(int /*argc*/, char ** argv, rpc_server_params params) {
    fprintf(stderr, "Usage: %s [options]\n\n", argv[0]);
    fprintf(stderr, "options:\n");
    fprintf(stderr, "  -h, --help            show this help message and exit\n");
    fprintf(stderr, "  -H HOST, --host HOST  host to bind to (default: %s)\n", params.host.c_str());
    fprintf(stderr, "  -p PORT, --port PORT  port to bind to (default: %d)\n", params.port);
    fprintf(stderr, "  -m MEM, --mem MEM     backend memory size (in MB)\n");
    fprintf(stderr, "\n");
}

static bool rpc_server_params_parse(int argc, char ** argv, rpc_server_params & params) {
    std::string arg;
    for (int i = 1; i < argc; i++) {
        arg = argv[i];
        if (arg == "-H" || arg == "--host") {
            if (++i >= argc) {
                return false;
            }
            params.host = argv[i];
        } else if (arg == "-p" || arg == "--port") {
            if (++i >= argc) {
                return false;
            }
            params.port = std::stoi(argv[i]);
            if (params.port <= 0 || params.port > 65535) {
                return false;
            }
        } else if (arg == "-m" || arg == "--mem") {
            if (++i >= argc) {
                return false;
            }
            params.backend_mem = std::stoul(argv[i]) * 1024 * 1024;
        } else if (arg == "-h" || arg == "--help") {
            print_usage(argc, argv, params);
            exit(0);
        } else {
            fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
            print_usage(argc, argv, params);
            exit(0);
        }
    }
    return true;
}

static ggml_backend_t create_backend() {
    ggml_backend_t backend = NULL;
#ifdef GGML_USE_CUDA
    fprintf(stderr, "%s: using CUDA backend\n", __func__);
    backend = ggml_backend_cuda_init(0); // init device 0
    if (!backend) {
        fprintf(stderr, "%s: ggml_backend_cuda_init() failed\n", __func__);
    }
#elif GGML_USE_METAL
    fprintf(stderr, "%s: using Metal backend\n", __func__);
    backend = ggml_backend_metal_init();
    if (!backend) {
        fprintf(stderr, "%s: ggml_backend_metal_init() failed\n", __func__);
    }
#elif GGML_USE_VULKAN
    fprintf(stderr, "%s: using Vulkan backend\n", __func__);
    backend = ggml_backend_vk_init(0); // init device 0
    if (!backend) {
        fprintf(stderr, "%s: ggml_backend_vulkan_init() failed\n", __func__);
    }
#endif

    // if there aren't GPU Backends fallback to CPU backend
    if (!backend) {
        fprintf(stderr, "%s: using CPU backend\n", __func__);
        backend = ggml_backend_cpu_init();
    }
    return backend;
}

static void get_backend_memory(size_t * free_mem, size_t * total_mem) {
#ifdef GGML_USE_CUDA
    ggml_backend_cuda_get_device_memory(0, free_mem, total_mem);
#elif GGML_USE_VULKAN
    ggml_backend_vk_get_device_memory(0, free_mem, total_mem);
#else
    #ifdef _WIN32
        MEMORYSTATUSEX status;
        status.dwLength = sizeof(status);
        GlobalMemoryStatusEx(&status);
        *total_mem = status.ullTotalPhys;
        *free_mem = status.ullAvailPhys;
    #else
        long pages = sysconf(_SC_PHYS_PAGES);
        long page_size = sysconf(_SC_PAGE_SIZE);
        *total_mem = pages * page_size;
        *free_mem = *total_mem;
    #endif
#endif
}

int main(int argc, char * argv[]) {
    rpc_server_params params;
    if (!rpc_server_params_parse(argc, argv, params)) {
        fprintf(stderr, "Invalid parameters\n");
        return 1;
    }

    if (params.host != "127.0.0.1") {
        fprintf(stderr, "\n");
        fprintf(stderr, "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n");
        fprintf(stderr, "WARNING: Host ('%s') is != '127.0.0.1'\n", params.host.c_str());
        fprintf(stderr, "         Never expose the RPC server to an open network!\n");
        fprintf(stderr, "         This is an experimental feature and is not secure!\n");
        fprintf(stderr, "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n");
        fprintf(stderr, "\n");
    }

    ggml_backend_t backend = create_backend();
    if (!backend) {
        fprintf(stderr, "Failed to create backend\n");
        return 1;
    }
    std::string endpoint = params.host + ":" + std::to_string(params.port);
    size_t free_mem, total_mem;
    if (params.backend_mem > 0) {
        free_mem = params.backend_mem;
        total_mem = params.backend_mem;
    } else {
        get_backend_memory(&free_mem, &total_mem);
    }
    printf("Starting RPC server on %s, backend memory: %zu MB\n", endpoint.c_str(), free_mem / (1024 * 1024));
    ggml_backend_rpc_start_server(backend, endpoint.c_str(), free_mem, total_mem);
    ggml_backend_free(backend);
    return 0;
}