rpc : add command line arg for specifying backend memory

ref: #7293

diff --git a/examples/rpc/README.md b/examples/rpc/README.md
index 325d0abc4b929c237adf48896d27b742af3bee4f..eeec71a8ee0c2e3ad9cd4c5faa28301d0bef1d98 100644 (file)
--- a/examples/rpc/README.md
+++ b/examples/rpc/README.md
@@ -42,7 +42,7 @@ cmake --build . --config Release
 Then, start the `rpc-server` with the backend:
 
 ```bash
-$ bin/rpc-server 0.0.0.0 50052
+$ bin/rpc-server -p 50052
 create_backend: using CUDA backend
 ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
 ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
@@ -53,7 +53,7 @@ Starting RPC server on 0.0.0.0:50052
 
 When using the CUDA backend, you can specify the device with the `CUDA_VISIBLE_DEVICES` environment variable, e.g.:
 ```bash
-$ CUDA_VISIBLE_DEVICES=0 bin/rpc-server 0.0.0.0 50052
+$ CUDA_VISIBLE_DEVICES=0 bin/rpc-server -p 50052
 ```
 This way you can run multiple `rpc-server` instances on the same host, each with a different CUDA device.
 

diff --git a/examples/rpc/rpc-server.cpp b/examples/rpc/rpc-server.cpp
index 496af84962de30e3a8acb074be1c3575569d1e73..021185b83cbbf794253ebb193d4cb55a1a35b869 100644 (file)
--- a/examples/rpc/rpc-server.cpp
+++ b/examples/rpc/rpc-server.cpp
@@ -10,6 +10,52 @@
 #include <string>
 #include <stdio.h>
 
+struct rpc_server_params {
+    std::string host        = "0.0.0.0";
+    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);
+        }
+    }
+    return true;
+}
+
 static ggml_backend_t create_backend() {
     ggml_backend_t backend = NULL;
 #ifdef GGML_USE_CUDA
@@ -45,14 +91,9 @@ static void get_backend_memory(size_t * free_mem, size_t * total_mem) {
 }
 
 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);
+    rpc_server_params params;
+    if (!rpc_server_params_parse(argc, argv, params)) {
+        fprintf(stderr, "Invalid parameters\n");
         return 1;
     }
     ggml_backend_t backend = create_backend();
@@ -60,10 +101,15 @@ int main(int argc, char * argv[]) {
         fprintf(stderr, "Failed to create backend\n");
         return 1;
     }
-    printf("Starting RPC server on %s:%d\n", host, port);
+    std::string endpoint = params.host + ":" + std::to_string(params.port);
     size_t free_mem, total_mem;
-    get_backend_memory(&free_mem, &total_mem);
-    std::string endpoint = std::string(host) + ":" + std::to_string(port);
+    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));
     start_rpc_server(backend, endpoint.c_str(), free_mem, total_mem);
     ggml_backend_free(backend);
     return 0;

diff --git a/ggml-rpc.cpp b/ggml-rpc.cpp
index efeacb297675b25b4f24e8fe86705e86c29f823c..ba392009ffed802607ef97a8f734ce6de1b7bdc0 100644 (file)
--- a/ggml-rpc.cpp
+++ b/ggml-rpc.cpp
@@ -28,7 +28,7 @@
 
 #define UNUSED GGML_UNUSED
 
-#define GGML_DEBUG 1
+#define GGML_DEBUG 0
 #if (GGML_DEBUG >= 1)
 #define GGML_PRINT_DEBUG(...) printf(__VA_ARGS__)
 #else