llama.cpp/examples/rpc/rpc-server.cpp

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

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

#include "ggml-rpc.h"
#include <string>
#include <stdio.h>

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__);
    }
#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);
#else
    // TODO: implement for other backends
    *free_mem = 1;
    *total_mem = 1;
#endif
}

int main(int argc, char * argv[]) {
    if (argc < 3) {
        fprintf(stderr, "Usage: %s <host> <port>\n", argv[0]);
        return 1;
    }
    const char * host = argv[1];
    int port = std::stoi(argv[2]);
    if (port <= 0 || port > 65535) {
        fprintf(stderr, "Invalid port number: %d\n", port);
        return 1;
    }
    ggml_backend_t backend = create_backend();
    if (!backend) {
        fprintf(stderr, "Failed to create backend\n");
        return 1;
    }
    printf("Starting RPC server on %s:%d\n", host, port);
    size_t free_mem, total_mem;
    get_backend_memory(&free_mem, &total_mem);
    std::string endpoint = std::string(host) + ":" + std::to_string(port);
    start_rpc_server(backend, endpoint.c_str(), free_mem, total_mem);
    ggml_backend_free(backend);
    return 0;
}