vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : add RPC backend (#6829)

Browse source 
* ggml : add RPC backend

The RPC backend proxies all operations to a remote server which runs a
regular backend (CPU, CUDA, Metal, etc).

* set TCP_NODELAY

* add CI workflows

* Address review comments

* fix warning

* implement llama_max_devices() for RPC

* Address review comments

* Address review comments

* wrap sockfd into a struct

* implement get_alignment and get_max_size

* add get_device_memory

* fix warning

* win32 support

* add README

* readme : trim trailing whitespace

* Address review comments

* win32 fix

* Address review comments

* fix compile warnings on macos
This commit is contained in:
Radoslav Gerganov 2024-05-14 14:27:19 +03:00 • committed by GitHub
parent 541600201e
commit 5e31828d3e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 1395 additions and 98 deletions
Download patch file Download diff file Expand all files Collapse all files

70
examples/rpc/rpc-server.cpp Normal file
View file

@ -0,0 +1,70 @@
#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;
}