Add RPC longhaul paging

tools/rpc/README.md

@@ -36,6 +36,17 @@ flowchart TD
 By default, `ggml-rpc-server` exposes all available accelerator devices on the host.
 If there are no accelerators, it exposes a single `CPU` device.
 
+For server-resident longhaul MoE paging, place the same GGUF shards on the RPC
+host and point the server at their directory:
+
+```sh
+$ bin/ggml-rpc-server --device MTL0 --longhaul-root /path/to/model-directory
+```
+
+The client can then use `--rpc`, `--longhaul`, and `--longhaul-cache` together.
+RPC longhaul v1 requires one remote Metal device. Expert cache misses are read
+from the RPC host's local files rather than uploaded by the client.
+
 ## Usage
 
 ### Remote hosts
@@ -107,4 +118,3 @@ Use the `GGML_RPC_DEBUG` environment variable to enable debug messages from `ggm
 ```bash
 $ GGML_RPC_DEBUG=1 bin/ggml-rpc-server
 ```
-

tools/rpc/rpc-server.cpp

@@ -13,6 +13,7 @@
 #include <algorithm>
 #include <clocale>
 #include <codecvt>
+#include <cstring>
 #include <filesystem>
 #include <regex>
 #include <stdio.h>
@@ -173,6 +174,7 @@ struct rpc_server_params {
     std::string              host        = "127.0.0.1";
     int                      port        = 50052;
     bool                     use_cache   = false;
+    std::string              longhaul_root;
     int                      n_threads   = std::max(1U, std::thread::hardware_concurrency()/2);
     std::vector<std::string> devices;
 };
@@ -186,6 +188,7 @@ static void print_usage(int /*argc*/, char ** argv, rpc_server_params params) {
     fprintf(stderr, "  -H, --host HOST                  host to bind to (default: %s)\n", params.host.c_str());
     fprintf(stderr, "  -p, --port PORT                  port to bind to (default: %d)\n", params.port);
     fprintf(stderr, "  -c, --cache                      enable local file cache\n");
+    fprintf(stderr, "      --longhaul-root PATH         serve longhaul expert data from this model directory\n");
     fprintf(stderr, "\n");
 }
 
@@ -233,6 +236,11 @@ static bool rpc_server_params_parse(int argc, char ** argv, rpc_server_params &
             }
         } else if (arg == "-c" || arg == "--cache") {
             params.use_cache = true;
+        } else if (arg == "--longhaul-root") {
+            if (++i >= argc) {
+                return false;
+            }
+            params.longhaul_root = argv[i];
         } else if (arg == "-h" || arg == "--help") {
             print_usage(argc, argv, params);
             exit(0);
@@ -313,6 +321,23 @@ int main(int argc, char * argv[]) {
         fprintf(stderr, "No devices found\n");
         return 1;
     }
+
+    if (!params.longhaul_root.empty()) {
+        std::error_code ec;
+        const auto root = std::filesystem::canonical(params.longhaul_root, ec);
+        if (ec || !std::filesystem::is_directory(root, ec)) {
+            fprintf(stderr, "Invalid longhaul root: %s\n", params.longhaul_root.c_str());
+            return 1;
+        }
+        params.longhaul_root = root.string();
+        for (auto * dev : devices) {
+            auto * dev_reg = ggml_backend_dev_backend_reg(dev);
+            if (!dev_reg || strcmp(ggml_backend_reg_name(dev_reg), "MTL") != 0) {
+                fprintf(stderr, "--longhaul-root currently requires Metal devices\n");
+                return 1;
+            }
+        }
+    }
     std::string endpoint = params.host + ":" + std::to_string(params.port);
     const char * cache_dir = nullptr;
     std::string cache_dir_str;
@@ -331,12 +356,19 @@ int main(int argc, char * argv[]) {
         return 1;
     }
 
-    auto start_server_fn = (decltype(ggml_backend_rpc_start_server)*) ggml_backend_reg_get_proc_address(reg, "ggml_backend_rpc_start_server");
+    auto start_server_fn = (decltype(ggml_backend_rpc_start_server_with_options)*)
+        ggml_backend_reg_get_proc_address(reg, "ggml_backend_rpc_start_server_with_options");
     if (!start_server_fn) {
-        fprintf(stderr, "Failed to obtain RPC backend start server function\n");
+        fprintf(stderr, "Failed to obtain RPC backend start server function with options\n");
         return 1;
     }
 
-    start_server_fn(endpoint.c_str(), cache_dir, params.n_threads, devices.size(), devices.data());
+    start_server_fn(
+        endpoint.c_str(),
+        cache_dir,
+        params.longhaul_root.empty() ? nullptr : params.longhaul_root.c_str(),
+        params.n_threads,
+        devices.size(),
+        devices.data());
     return 0;
 }