Rpc improvement

CMakeLists.txt

@@ -6,7 +6,6 @@ include(CheckIncludeFileCXX)
 set(CMAKE_WARN_UNUSED_CLI YES)
 
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
-
 set(CMAKE_CXX_STANDARD 17)
 set(CMAKE_CXX_STANDARD_REQUIRED true)
 

common/common.cpp

@@ -81,7 +81,9 @@
 #endif
 #define LLAMA_CURL_MAX_URL_LENGTH 2084 // Maximum URL Length in Chrome: 2083
 #endif // LLAMA_USE_CURL
-
+#ifdef GGML_USE_RPC
+#  include "ggml-rpc.h"
+#endif
 using json = nlohmann::ordered_json;
 
 //
@@ -989,6 +991,35 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
     if (arg == "--rpc") {
         CHECK_ARG
         params.rpc_servers = argv[i];
+        std::string servers(params.rpc_servers);
+        size_t pos = 0;
+        while ((pos = servers.find(",")) != std::string::npos) {
+            std::string server = servers.substr(0, pos);
+            ggml_backend_rpc_buffer_type(server.c_str());            
+            servers.erase(0, pos + 1);
+        }
+        ggml_backend_rpc_buffer_type(servers.c_str());
+        return true;
+    }
+    if (arg == "--override-kv") {
+        CHECK_ARG
+            if (!string_parse_kv_override(argv[i], params.kv_overrides)) {
+                fprintf(stderr, "error: Invalid type for KV override: %s\n", argv[i]);
+                invalid_param = true;
+                return true;
+            }
+        return true;
+    }
+    if (arg == "--override-tensor" || arg == "-ot") {
+        CHECK_ARG
+            /*for (auto endpoint : params.rpc_servers.split)
+            {
+
+            }*/
+        if (!parse_buft_overrides(std::string{ argv[i] }, params.tensor_buft_overrides)) {
+            fprintf(stderr, "error: Invalid tensor buffer type override: %s\n", argv[i]);
+            invalid_param = true;
+        }
         return true;
     }
     if (arg == "--no-mmap") {
@@ -1196,23 +1227,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
         sparams.grammar = json_schema_to_grammar(json::parse(argv[i]));
         return true;
     }
-    if (arg == "--override-kv") {
-        CHECK_ARG
-        if (!string_parse_kv_override(argv[i], params.kv_overrides)) {
-            fprintf(stderr, "error: Invalid type for KV override: %s\n", argv[i]);
-            invalid_param = true;
-            return true;
-        }
-        return true;
-    }
-    if (arg == "--override-tensor" || arg == "-ot") {
-        CHECK_ARG
-        if (!parse_buft_overrides(std::string{argv[i]}, params.tensor_buft_overrides)) {
-            fprintf(stderr, "error: Invalid tensor buffer type override: %s\n", argv[i]);
-            invalid_param = true;
-        }
-        return true;
-    }
+
     if (arg == "--offload-policy" || arg == "-op") {
         CHECK_ARG
         auto p = string_split_pairs<int,int>(argv[i], ',');

examples/rpc/CMakeLists.txt

@@ -1,2 +1,4 @@
-add_executable(rpc-server rpc-server.cpp)
-target_link_libraries(rpc-server PRIVATE ggml llama)
+set(TARGET rpc-server)
+add_executable(${TARGET} rpc-server.cpp)
+target_link_libraries(${TARGET} PRIVATE ggml)
+target_compile_features(${TARGET} PRIVATE cxx_std_17)

examples/rpc/rpc-server.cpp

@@ -5,33 +5,166 @@
 #ifdef GGML_USE_METAL
 #include "ggml-metal.h"
 #endif
+#ifdef GGML_USE_VULKAN
+#include "ggml-vulkan.h"
+#endif
+#ifdef GGML_USE_SYCL
+#include "ggml-sycl.h"
+#endif
 
 #include "ggml-rpc.h"
 #ifdef _WIN32
+#  define DIRECTORY_SEPARATOR '\\'
+#  define NOMINMAX
+#  include <locale>
 #  include <windows.h>
+#  include <fcntl.h>
+#  include <io.h>
 #else
+#  define DIRECTORY_SEPARATOR '/'
 #  include <unistd.h>
+#  include <sys/stat.h>
 #endif
 #include <string>
 #include <stdio.h>
+#include <algorithm>
+#include <thread>
+#include <fstream>
+#include <filesystem>
+#include <codecvt>
+
+namespace fs = std::filesystem;
+
+// NOTE: this is copied from common.cpp to avoid linking with libcommon
+// returns true if successful, false otherwise
+static bool fs_create_directory_with_parents(const std::string& path) {
+#ifdef _WIN32
+    std::wstring_convert<std::codecvt_utf8<wchar_t>> converter;
+    std::wstring wpath = converter.from_bytes(path);
+
+    // if the path already exists, check whether it's a directory
+    const DWORD attributes = GetFileAttributesW(wpath.c_str());
+    if ((attributes != INVALID_FILE_ATTRIBUTES) && (attributes & FILE_ATTRIBUTE_DIRECTORY)) {
+        return true;
+    }
+
+    size_t pos_slash = 0;
+
+    // process path from front to back, procedurally creating directories
+    while ((pos_slash = path.find('\\', pos_slash)) != std::string::npos) {
+        const std::wstring subpath = wpath.substr(0, pos_slash);
+        const wchar_t* test = subpath.c_str();
+
+        const bool success = CreateDirectoryW(test, NULL);
+        if (!success) {
+            const DWORD error = GetLastError();
+
+            // if the path already exists, ensure that it's a directory
+            if (error == ERROR_ALREADY_EXISTS) {
+                const DWORD attributes = GetFileAttributesW(subpath.c_str());
+                if (attributes == INVALID_FILE_ATTRIBUTES || !(attributes & FILE_ATTRIBUTE_DIRECTORY)) {
+                    return false;
+                }
+            }
+            else {
+                return false;
+            }
+        }
+
+        pos_slash += 1;
+    }
+
+    return true;
+#else
+    // if the path already exists, check whether it's a directory
+    struct stat info;
+    if (stat(path.c_str(), &info) == 0) {
+        return S_ISDIR(info.st_mode);
+    }
+
+    size_t pos_slash = 1; // skip leading slashes for directory creation
+
+    // process path from front to back, procedurally creating directories
+    while ((pos_slash = path.find('/', pos_slash)) != std::string::npos) {
+        const std::string subpath = path.substr(0, pos_slash);
+        struct stat info;
+
+        // if the path already exists, ensure that it's a directory
+        if (stat(subpath.c_str(), &info) == 0) {
+            if (!S_ISDIR(info.st_mode)) {
+                return false;
+            }
+        }
+        else {
+            // create parent directories
+            const int ret = mkdir(subpath.c_str(), 0755);
+            if (ret != 0) {
+                return false;
+            }
+        }
+
+        pos_slash += 1;
+    }
+
+    return true;
+#endif // _WIN32
+}
+
+// NOTE: this is copied from common.cpp to avoid linking with libcommon
+static std::string fs_get_cache_directory() {
+    std::string cache_directory = "";
+    auto ensure_trailing_slash = [](std::string p) {
+        // Make sure to add trailing slash
+        if (p.back() != DIRECTORY_SEPARATOR) {
+            p += DIRECTORY_SEPARATOR;
+        }
+        return p;
+    };
+    if (getenv("LLAMA_CACHE")) {
+        cache_directory = std::getenv("LLAMA_CACHE");
+    }
+    else {
+#if defined(__linux__) || defined(__FreeBSD__) || defined(_AIX)
+        if (std::getenv("XDG_CACHE_HOME")) {
+            cache_directory = std::getenv("XDG_CACHE_HOME");
+        }
+        else {
+            cache_directory = std::getenv("HOME") + std::string("/.cache/");
+        }
+#elif defined(__APPLE__)
+        cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
+#elif defined(_WIN32)
+        cache_directory = std::getenv("LOCALAPPDATA");
+#else
+#  error Unknown architecture
+#endif
+        cache_directory = ensure_trailing_slash(cache_directory);
+        cache_directory += "llama.cpp";
+    }
+    return ensure_trailing_slash(cache_directory);
+}
 
 struct rpc_server_params {
     std::string host        = "127.0.0.1";
     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) {
+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, "  -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");
+    fprintf(stderr, "  -c,      --cache          enable local file cache\n");
     fprintf(stderr, "\n");
 }
 
-static bool rpc_server_params_parse(int argc, char ** argv, rpc_server_params & params) {
+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];
@@ -40,23 +173,40 @@ static bool rpc_server_params_parse(int argc, char ** argv, rpc_server_params &
                 return false;
             }
             params.host = argv[i];
-        } else if (arg == "-p" || arg == "--port") {
+        }
+        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;
             }
             params.port = std::stoi(argv[i]);
             if (params.port <= 0 || params.port > 65535) {
                 return false;
             }
-        } else if (arg == "-m" || arg == "--mem") {
+        }
+        else if (arg == "-c" || arg == "--cache") {
+            params.use_cache = true;
+        }
+        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") {
+        }
+        else if (arg == "-h" || arg == "--help") {
             print_usage(argc, argv, params);
             exit(0);
-        } else {
+        }
+        else {
             fprintf(stderr, "error: unknown argument: %s\n", arg.c_str());
             print_usage(argc, argv, params);
             exit(0);
@@ -65,7 +215,7 @@ 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__);
@@ -79,19 +229,36 @@ static ggml_backend_t create_backend() {
     if (!backend) {
         fprintf(stderr, "%s: ggml_backend_metal_init() failed\n", __func__);
     }
+#elif GGML_USE_VULKAN
+    fprintf(stderr, "%s: using Vulkan backend\n", __func__);
+    backend = ggml_backend_vk_init(0); // init device 0
+    if (!backend) {
+        fprintf(stderr, "%s: ggml_backend_vulkan_init() failed\n", __func__);
+    }
+#elif GGML_USE_SYCL
+    fprintf(stderr, "%s: using SYCL backend\n", __func__);
+    backend = ggml_backend_sycl_init(0); // init device 0
+    if (!backend) {
+        fprintf(stderr, "%s: ggml_backend_sycl_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();
+        ggml_backend_cpu_set_n_threads(backend, params.n_threads);
     }
     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);
+#elif GGML_USE_VULKAN
+    ggml_backend_vk_get_device_memory(0, free_mem, total_mem);
+#elif GGML_USE_SYCL
+    ggml_backend_sycl_get_device_memory(0, free_mem, total_mem);
 #else
     #ifdef _WIN32
         MEMORYSTATUSEX status;
@@ -125,7 +292,7 @@ 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;
@@ -135,11 +302,28 @@ int main(int argc, char * argv[]) {
     if (params.backend_mem > 0) {
         free_mem = params.backend_mem;
         total_mem = params.backend_mem;
-    } else {
+    }
+    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);
+    const char * cache_dir = nullptr;
+    std::string cache_dir_str;
+    if (params.use_cache) {
+        cache_dir_str = fs_get_cache_directory() + "rpc/";
+        if (!fs_create_directory_with_parents(cache_dir_str)) {
+            fprintf(stderr, "Failed to create cache directory: %s\n", cache_dir_str.c_str());
+            return 1;
+        }
+        cache_dir = cache_dir_str.c_str();
+    }
+    printf("Starting RPC server v%d.%d.%d\n",
+        RPC_PROTO_MAJOR_VERSION,
+        RPC_PROTO_MINOR_VERSION,
+        RPC_PROTO_PATCH_VERSION);
+    printf("  endpoint       : %s\n", endpoint.c_str());
+    printf("  local cache    : %s\n", cache_dir ? cache_dir : "n/a");
+    printf("  backend memory : %zu MB\n", free_mem / (1024 * 1024));
+    ggml_backend_rpc_start_server(backend, endpoint.c_str(), cache_dir, free_mem, total_mem);
     ggml_backend_free(backend);
     return 0;
 }