Skip to content

rpc : add command line option for number of threads for the CPU backend #13060

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 23, 2025
Merged

rpc : add command line option for number of threads for the CPU backend #13060

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions examples/rpc/rpc-server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@

#include "ggml-rpc.h"
#ifdef _WIN32
# define NOMINMAX
# define DIRECTORY_SEPARATOR '\\'
# include <locale>
# include <windows.h>
Expand All @@ -37,6 +38,8 @@
#include <stdio.h>
#include <vector>
#include <filesystem>
#include <algorithm>
#include <thread>

namespace fs = std::filesystem;

Expand Down Expand Up @@ -150,12 +153,14 @@ struct rpc_server_params {
int port = 50052;
size_t backend_mem = 0;
bool use_cache = false;
int n_threads = std::max(1U, std::thread::hardware_concurrency()/2);
};

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, " -t, --threads number of threads for the CPU backend (default: %d)\n", params.n_threads);
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");
Expand All @@ -172,6 +177,15 @@ static bool rpc_server_params_parse(int argc, char ** argv, rpc_server_params &
return false;
}
params.host = argv[i];
} else if (arg == "-t" || arg == "--threads") {
if (++i >= argc) {
return false;
}
params.n_threads = std::stoi(argv[i]);
if (params.n_threads <= 0) {
fprintf(stderr, "error: invalid number of threads: %d\n", params.n_threads);
return false;
}
} else if (arg == "-p" || arg == "--port") {
if (++i >= argc) {
return false;
Expand Down Expand Up @@ -199,7 +213,7 @@ static bool rpc_server_params_parse(int argc, char ** argv, rpc_server_params &
return true;
}

static ggml_backend_t create_backend() {
static ggml_backend_t create_backend(const rpc_server_params & params) {
ggml_backend_t backend = NULL;
#ifdef GGML_USE_CUDA
fprintf(stderr, "%s: using CUDA backend\n", __func__);
Expand Down Expand Up @@ -231,6 +245,7 @@ static ggml_backend_t create_backend() {
if (!backend) {
fprintf(stderr, "%s: using CPU backend\n", __func__);
backend = ggml_backend_cpu_init();
ggml_backend_cpu_set_n_threads(backend, params.n_threads);
}
return backend;
}
Expand Down Expand Up @@ -275,7 +290,7 @@ int main(int argc, char * argv[]) {
fprintf(stderr, "\n");
}

ggml_backend_t backend = create_backend();
ggml_backend_t backend = create_backend(params);
if (!backend) {
fprintf(stderr, "Failed to create backend\n");
return 1;
Expand Down
Loading