Revert "Rpc improvement (#480)"

This reverts commit 8a5f8573aefc23282200041abbfa12886083334a.

11 files changed, 484 insertions, 1234 deletions

diff --git a/CMakeLists.txt b/CMakeLists.txt
index edb9e657..3e9c3cc0 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -6,6 +6,7 @@ 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)
 
diff --git a/common/common.cpp b/common/common.cpp
index 569c2ecd..232101e4 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -81,9 +81,7 @@
 #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;
 
 //
@@ -1006,35 +1004,6 @@ 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") {
@@ -1242,7 +1211,23 @@ 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], ',');
diff --git a/examples/rpc/CMakeLists.txt b/examples/rpc/CMakeLists.txt
index 41b22863..ae48fb98 100644
--- a/examples/rpc/CMakeLists.txt
+++ b/examples/rpc/CMakeLists.txt
@@ -1,4 +1,2 @@
-set(TARGET rpc-server)
-add_executable(${TARGET} rpc-server.cpp)
-target_link_libraries(${TARGET} PRIVATE ggml)
-target_compile_features(${TARGET} PRIVATE cxx_std_17)
\ No newline at end of file
+add_executable(rpc-server rpc-server.cpp)
+target_link_libraries(rpc-server PRIVATE ggml llama)
diff --git a/examples/rpc/rpc-server.cpp b/examples/rpc/rpc-server.cpp
index 943c1b1c..6342e648 100644
--- a/examples/rpc/rpc-server.cpp
+++ b/examples/rpc/rpc-server.cpp
@@ -5,166 +5,33 @@
 #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, "  -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, "  -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) {
+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];
@@ -173,18 +40,7 @@ static bool rpc_server_params_parse(int argc, char** argv, rpc_server_params& pa
                 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") {
+        } else if (arg == "-p" || arg == "--port") {
             if (++i >= argc) {
                 return false;
             }
@@ -192,21 +48,15 @@ static bool rpc_server_params_parse(int argc, char** argv, rpc_server_params& pa
             if (params.port <= 0 || params.port > 65535) {
                 return false;
             }
-        }
-        else if (arg == "-c" || arg == "--cache") {
-            params.use_cache = true;
-        }
-        else if (arg == "-m" || arg == "--mem") {
+        } 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);
@@ -215,7 +65,7 @@ static bool rpc_server_params_parse(int argc, char** argv, rpc_server_params& pa
     return true;
 }
 
-static ggml_backend_t create_backend(const rpc_server_params& params) {
+static ggml_backend_t create_backend() {
     ggml_backend_t backend = NULL;
 #ifdef GGML_USE_CUDA
     fprintf(stderr, "%s: using CUDA backend\n", __func__);
@@ -229,25 +79,12 @@ static ggml_backend_t create_backend(const rpc_server_params& params) {
     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;
 }
@@ -255,10 +92,6 @@ static ggml_backend_t create_backend(const rpc_server_params& params) {
 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;
@@ -292,7 +125,7 @@ int main(int argc, char * argv[]) {
         fprintf(stderr, "\n");
     }
 
-    ggml_backend_t backend = create_backend(params);
+    ggml_backend_t backend = create_backend();
     if (!backend) {
         fprintf(stderr, "Failed to create backend\n");
         return 1;
@@ -302,28 +135,11 @@ 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);
     }
-    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);
+    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/examples/server/server.cpp b/examples/server/server.cpp
index 9e80bd7e..acd0581e 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -12,8 +12,6 @@
 #endif
 // increase max payload length to allow use of larger context size
 #define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
-// disable Nagle's algorithm
-#define CPPHTTPLIB_TCP_NODELAY true
 #include "httplib.h"
 // Change JSON_ASSERT from assert() to GGML_ASSERT:
 #define JSON_ASSERT GGML_ASSERT
diff --git a/examples/server/utils.hpp b/examples/server/utils.hpp
index 1aaa445e..70be0748 100644
--- a/examples/server/utils.hpp
+++ b/examples/server/utils.hpp
@@ -6,6 +6,7 @@
 // Change JSON_ASSERT from assert() to GGML_ASSERT:
 #define JSON_ASSERT GGML_ASSERT
 #include "json.hpp"
+
 #include <string>
 #include <vector>
 #include <sstream>
diff --git a/ggml/include/ggml-rpc.h b/ggml/include/ggml-rpc.h
index 549e8504..aa144832 100644
--- a/ggml/include/ggml-rpc.h
+++ b/ggml/include/ggml-rpc.h
@@ -7,9 +7,6 @@
 extern "C" {
 #endif
 
-#define RPC_PROTO_MAJOR_VERSION    2
-#define RPC_PROTO_MINOR_VERSION    0
-#define RPC_PROTO_PATCH_VERSION    1
 #define GGML_RPC_MAX_SERVERS       16
 
 // backend API
@@ -20,9 +17,7 @@ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const
 
 GGML_API GGML_CALL void ggml_backend_rpc_get_device_memory(const char * endpoint, size_t * free, size_t * total);
 
-GGML_API GGML_CALL void ggml_backend_rpc_start_server(ggml_backend_t backend, const char * endpoint,
-                                                    const char * cache_dir,
-                                                    size_t free_mem, size_t total_mem);
+GGML_API GGML_CALL void start_rpc_server(ggml_backend_t backend, const char * endpoint, size_t free_mem, size_t total_mem);
 
 #ifdef  __cplusplus
 }
diff --git a/ggml/src/ggml-backend.c b/ggml/src/ggml-backend.c
index 5903c89c..e191c2d9 100644
--- a/ggml/src/ggml-backend.c
+++ b/ggml/src/ggml-backend.c
@@ -1,7 +1,6 @@
 #include "ggml-backend-impl.h"
 #include "ggml-alloc.h"
 #include "ggml-impl.h"
-#include "ggml-rpc.h"
 
 #include <assert.h>
 #include <limits.h>
@@ -469,10 +468,6 @@ GGML_CALL static void ggml_backend_registry_init(void) {
     extern GGML_CALL int ggml_backend_cann_reg_devices(void);
     ggml_backend_cann_reg_devices();
 #endif
-#ifdef GGML_USE_RPC
-    extern GGML_CALL void ggml_backend_rpc_reg_devices(void);
-    ggml_backend_rpc_reg_devices();
-#endif
 }
 
 GGML_CALL void ggml_backend_register(const char * name, ggml_backend_init_fn init_fn, ggml_backend_buffer_type_t default_buffer_type, void * user_data) {
@@ -948,13 +943,6 @@ GGML_CALL static ggml_backend_t ggml_backend_reg_cpu_init(const char * params, v
     GGML_UNUSED(user_data);
 }
 
-GGML_CALL static ggml_backend_t ggml_backend_reg_rpc_init(const char* params, void* user_data) {
-    return ggml_backend_rpc_init((const char*)user_data);
-
-    GGML_UNUSED(params);
-    GGML_UNUSED(user_data);
-}
-
 // multi-buffer buffer
 
 struct ggml_backend_multi_buffer_context {
diff --git a/ggml/src/ggml-rpc.cpp b/ggml/src/ggml-rpc.cpp
index 3b5c8f46..7757615f 100644
--- a/ggml/src/ggml-rpc.cpp
+++ b/ggml/src/ggml-rpc.cpp
@@ -26,10 +26,7 @@
 #  include <unistd.h>
 #endif
 #include <string.h>
-#include <fstream>
-#include <filesystem>
 
-namespace fs = std::filesystem;
 #define UNUSED GGML_UNUSED
 
 #define GGML_DEBUG 0
@@ -79,114 +76,27 @@ struct rpc_tensor {
 
     char padding[4];
 };
+#pragma pack(pop)
 
 static_assert(sizeof(rpc_tensor) % 8 == 0, "rpc_tensor size must be multiple of 8");
-static std::unordered_map<std::string, std::string> rpc_server_map;
+
 // RPC commands
 enum rpc_cmd {
-    RPC_CMD_ALLOC_BUFFER = 0,
-    RPC_CMD_GET_ALIGNMENT,
-    RPC_CMD_GET_MAX_SIZE,
-    RPC_CMD_BUFFER_GET_BASE,
-    RPC_CMD_FREE_BUFFER,
-    RPC_CMD_BUFFER_CLEAR,
-    RPC_CMD_SET_TENSOR,
-    RPC_CMD_SET_TENSOR_HASH,
-    RPC_CMD_GET_TENSOR,
-    RPC_CMD_COPY_TENSOR,
-    RPC_CMD_GRAPH_COMPUTE,
-    RPC_CMD_GET_DEVICE_MEMORY,
-    RPC_CMD_INIT_TENSOR,
-    RPC_CMD_GET_ALLOC_SIZE,
-    RPC_CMD_HELLO,
-    RPC_CMD_COUNT,
-};
-
-// Try RPC_CMD_SET_TENSOR_HASH first when data size is larger than this threshold
-const size_t HASH_THRESHOLD = 10 * 1024 * 1024;
-
-struct rpc_msg_hello_rsp {
-    uint8_t major;
-    uint8_t minor;
-    uint8_t patch;
-};
-
-struct rpc_msg_get_alloc_size_req {
-    rpc_tensor tensor;
-};
-
-struct rpc_msg_get_alloc_size_rsp {
-    uint64_t alloc_size;
-};
-
-struct rpc_msg_init_tensor_req {
-    rpc_tensor tensor;
+    ALLOC_BUFFER = 0,
+    GET_ALIGNMENT,
+    GET_MAX_SIZE,
+    BUFFER_GET_BASE,
+    FREE_BUFFER,
+    BUFFER_CLEAR,
+    SET_TENSOR,
+    GET_TENSOR,
+    COPY_TENSOR,
+    GRAPH_COMPUTE,
+    GET_DEVICE_MEMORY,
 };
 
-struct rpc_msg_alloc_buffer_req {
-    uint64_t size;
-};
-
-struct rpc_msg_alloc_buffer_rsp {
-    uint64_t remote_ptr;
-    uint64_t remote_size;
-};
-
-struct rpc_msg_get_alignment_rsp {
-    uint64_t alignment;
-};
-
-struct rpc_msg_get_max_size_rsp {
-    uint64_t max_size;
-};
-
-struct rpc_msg_buffer_get_base_req {
-    uint64_t remote_ptr;
-};
-
-struct rpc_msg_buffer_get_base_rsp {
-    uint64_t base_ptr;
-};
-
-struct rpc_msg_free_buffer_req {
-    uint64_t remote_ptr;
-};
-
-struct rpc_msg_buffer_clear_req {
-    uint64_t remote_ptr;
-    uint8_t value;
-};
-
-struct rpc_msg_set_tensor_hash_rsp {
-    uint8_t result;
-};
-
-struct rpc_msg_get_tensor_req {
-    rpc_tensor tensor;
-    uint64_t offset;
-    uint64_t size;
-};
-
-struct rpc_msg_copy_tensor_req {
-    rpc_tensor src;
-    rpc_tensor dst;
-};
-
-struct rpc_msg_copy_tensor_rsp {
-    uint8_t result;
-};
-
-struct rpc_msg_graph_compute_rsp {
-    uint8_t result;
-};
-
-struct rpc_msg_get_device_memory_rsp {
-    uint64_t free_mem;
-    uint64_t total_mem;
-};
-#pragma pack(pop)
-
 // RPC data structures
+
 static ggml_guid_t ggml_backend_rpc_guid() {
     static ggml_guid guid = {0x99, 0x68, 0x5b, 0x6c, 0xd2, 0x83, 0x3d, 0x24, 0x25, 0x36, 0x72, 0xe1, 0x5b, 0x0e, 0x14, 0x03};
     return &guid;
@@ -206,26 +116,13 @@ struct ggml_backend_rpc_context {
 
 struct ggml_backend_rpc_buffer_context {
     std::shared_ptr<socket_t> sock;
-    //std::unordered_map<ggml_backend_buffer_t, void *> base_cache;
-    void* base_ptr;
+    std::unordered_map<ggml_backend_buffer_t, void *> base_cache;
     uint64_t remote_ptr;
     std::string name;
 };
 
 // RPC helper functions
 
-// Computes FNV-1a hash of the data
-static uint64_t fnv_hash(const uint8_t* data, size_t len) {
-    const uint64_t fnv_prime = 0x100000001b3ULL;
-    uint64_t hash = 0xcbf29ce484222325ULL;
-
-    for (size_t i = 0; i < len; ++i) {
-        hash ^= data[i];
-        hash *= fnv_prime;
-    }
-    return hash;
-}
-
 static std::shared_ptr<socket_t> make_socket(sockfd_t fd) {
 #ifdef _WIN32
     if (fd == INVALID_SOCKET) {
@@ -342,39 +239,6 @@ static bool recv_data(sockfd_t sockfd, void * data, size_t size) {
     return true;
 }
 
-static bool send_msg(sockfd_t sockfd, const void* msg, size_t msg_size) {
-    if (!send_data(sockfd, &msg_size, sizeof(msg_size))) {
-        return false;
-    }
-    return send_data(sockfd, msg, msg_size);
-}
-
-static bool recv_msg(sockfd_t sockfd, void* msg, size_t msg_size) {
-    uint64_t size;
-    if (!recv_data(sockfd, &size, sizeof(size))) {
-        return false;
-    }
-    if (size != msg_size) {
-        return false;
-    }
-    return recv_data(sockfd, msg, msg_size);
-}
-
-static bool recv_msg(sockfd_t sockfd, std::vector<uint8_t>& input) {
-    uint64_t size;
-    if (!recv_data(sockfd, &size, sizeof(size))) {
-        return false;
-    }
-    try {
-        input.resize(size);
-    }
-    catch (const std::bad_alloc& e) {
-        fprintf(stderr, "Failed to allocate input buffer of size %" PRIu64 "\n", size);
-        return false;
-    }
-    return recv_data(sockfd, input.data(), size);
-}
-
 static bool parse_endpoint(const std::string & endpoint, std::string & host, int & port) {
     size_t pos = endpoint.find(':');
     if (pos == std::string::npos) {
@@ -386,56 +250,35 @@ static bool parse_endpoint(const std::string & endpoint, std::string & host, int
 }
 
 // RPC request : | rpc_cmd (1 byte) | request_size (8 bytes) | request_data (request_size bytes) |
-// No response
-static bool send_rpc_cmd(const std::shared_ptr<socket_t> & sock, enum rpc_cmd cmd, const void * input, size_t input_size) {
+// RPC response: | response_size (8 bytes) | response_data (response_size bytes) |
+static bool send_rpc_cmd(const std::shared_ptr<socket_t> & sock, enum rpc_cmd cmd, const std::vector<uint8_t> & input, std::vector<uint8_t> & output) {
     uint8_t cmd_byte = cmd;
     if (!send_data(sock->fd, &cmd_byte, sizeof(cmd_byte))) {
         return false;
     }
+    uint64_t input_size = input.size();
     if (!send_data(sock->fd, &input_size, sizeof(input_size))) {
         return false;
     }
-    if (!send_data(sock->fd, input, input_size)) {
-        return false;
-    }
-    return true;
-}
-
-// RPC request : | rpc_cmd (1 byte) | request_size (8 bytes) | request_data (request_size bytes) |
-// RPC response: | response_size (8 bytes) | response_data (response_size bytes) |
-static bool send_rpc_cmd(const std::shared_ptr<socket_t> & sock, enum rpc_cmd cmd, const void * input, size_t input_size, void * output, size_t output_size) {
-    if (!send_rpc_cmd(sock, cmd, input, input_size)) {
+    if (!send_data(sock->fd, input.data(), input.size())) {
         return false;
     }
-    // TODO: currently the output_size is always known, do we need support for commands with variable output size?
-    // even if we do, we can skip sending output_size from the server for commands with known output size
-    uint64_t out_size;
-    if (!recv_data(sock->fd, &out_size, sizeof(out_size))) {
+    uint64_t output_size;
+    if (!recv_data(sock->fd, &output_size, sizeof(output_size))) {
         return false;
     }
-    if (out_size != output_size) {
-        return false;
+    if (output_size == 0) {
+        output.clear();
+        return true;
     }
-    if (!recv_data(sock->fd, output, output_size)) {
+    output.resize(output_size);
+    if (!recv_data(sock->fd, output.data(), output_size)) {
         return false;
     }
     return true;
 }
 
 // RPC client-side implementation
-static bool check_server_version(const std::shared_ptr<socket_t>& sock) {
-    rpc_msg_hello_rsp response;
-    bool status = send_rpc_cmd(sock, RPC_CMD_HELLO, nullptr, 0, &response, sizeof(response));
-    GGML_ASSERT(status);
-    if (response.major != RPC_PROTO_MAJOR_VERSION || response.minor > RPC_PROTO_MINOR_VERSION) {
-        fprintf(stderr, "RPC server version mismatch: %d.%d.%d\n", response.major, response.minor, response.patch);
-        return false;
-    }
-    if (response.minor != RPC_PROTO_MINOR_VERSION || response.patch != RPC_PROTO_PATCH_VERSION) {
-        fprintf(stderr, "WARNING: RPC server version mismatch: %d.%d.%d\n", response.major, response.minor, response.patch);
-    }
-    return true;
-}
 
 static std::shared_ptr<socket_t> get_socket(const std::string & endpoint) {
     static std::mutex mutex;
@@ -470,9 +313,6 @@ static std::shared_ptr<socket_t> get_socket(const std::string & endpoint) {
     if (sock == nullptr) {
         return nullptr;
     }
-    if (!check_server_version(sock)) {
-        return nullptr;
-    }
     GGML_PRINT_DEBUG("[%s] connected to %s, sockfd=%d\n", __func__, endpoint.c_str(), sock->fd);
     sockets[endpoint] = sock;
     return sock;
@@ -483,29 +323,40 @@ GGML_CALL static const char * ggml_backend_rpc_buffer_get_name(ggml_backend_buff
     return ctx->name.c_str();
 }
 
-
-static void ggml_backend_rpc_buffer_free_buffer(ggml_backend_buffer_t buffer) {
-    ggml_backend_rpc_buffer_context* ctx = (ggml_backend_rpc_buffer_context*)buffer->context;
-    rpc_msg_free_buffer_req request = { ctx->remote_ptr };
-    bool status = send_rpc_cmd(ctx->sock, RPC_CMD_FREE_BUFFER, &request, sizeof(request), nullptr, 0);
+GGML_CALL static void ggml_backend_rpc_buffer_free_buffer(ggml_backend_buffer_t buffer) {
+    ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
+    // input serialization format: | remote_ptr (8 bytes) |
+    std::vector<uint8_t> input(sizeof(uint64_t), 0);
+    uint64_t remote_ptr = ctx->remote_ptr;
+    memcpy(input.data(), &remote_ptr, sizeof(remote_ptr));
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(ctx->sock, FREE_BUFFER, input, output);
     GGML_ASSERT(status);
+    GGML_ASSERT(output.empty());
     delete ctx;
 }
 
-static void* ggml_backend_rpc_buffer_get_base(ggml_backend_buffer_t buffer) {
-    ggml_backend_rpc_buffer_context* ctx = (ggml_backend_rpc_buffer_context*)buffer->context;
-    if (ctx->base_ptr != nullptr) {
-        return ctx->base_ptr;
-    }
-    rpc_msg_buffer_get_base_req request = { ctx->remote_ptr };
-    rpc_msg_buffer_get_base_rsp response;
-    bool status = send_rpc_cmd(ctx->sock, RPC_CMD_BUFFER_GET_BASE, &request, sizeof(request), &response, sizeof(response));
+GGML_CALL static void * ggml_backend_rpc_buffer_get_base(ggml_backend_buffer_t buffer) {
+    ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
+    if (ctx->base_cache.find(buffer) != ctx->base_cache.end()) {
+        return ctx->base_cache[buffer];
+    }
+    // input serialization format: | remote_ptr (8 bytes) |
+    std::vector<uint8_t> input(sizeof(uint64_t), 0);
+    uint64_t remote_ptr = ctx->remote_ptr;
+    memcpy(input.data(), &remote_ptr, sizeof(remote_ptr));
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(ctx->sock, BUFFER_GET_BASE, input, output);
     GGML_ASSERT(status);
-    ctx->base_ptr = reinterpret_cast<void*>(response.base_ptr);
-    return ctx->base_ptr;
+    GGML_ASSERT(output.size() == sizeof(uint64_t));
+    // output serialization format: | base_ptr (8 bytes) |
+    uint64_t base_ptr;
+    memcpy(&base_ptr, output.data(), sizeof(base_ptr));
+    void * base = reinterpret_cast<void *>(base_ptr);
+    ctx->base_cache[buffer] = base;
+    return base;
 }
 
-
 static rpc_tensor serialize_tensor(const ggml_tensor * tensor) {
     rpc_tensor result;
     result.id = reinterpret_cast<uint64_t>(tensor);
@@ -532,100 +383,86 @@ static rpc_tensor serialize_tensor(const ggml_tensor * tensor) {
     result.view_src = reinterpret_cast<uint64_t>(tensor->view_src);
     result.view_offs = tensor->view_offs;
     result.data = reinterpret_cast<uint64_t>(tensor->data);
-
-    // Avoid sending uninitialized data over the wire
-    memset(result.name, 0, sizeof(result.name));
-    memset(result.padding, 0, sizeof(result.padding));
-
     snprintf(result.name, GGML_MAX_NAME, "%s", tensor->name);
     return result;
 }
 
-
-GGML_CALL static void ggml_backend_rpc_buffer_init_tensor(ggml_backend_buffer_t buffer, ggml_tensor* tensor) {
-    ggml_backend_rpc_buffer_context* ctx = (ggml_backend_rpc_buffer_context*)buffer->context;
-
-    // CUDA backend on the server pads everything to 512 due to CUDA limitations.
-    // Due to bandwidth constraints, we only call the server init tensor functions if necessary.
-    // In particular, only quantized tensors need padding
-    if (ggml_is_quantized(tensor->type) && (tensor->ne[0] % 512 != 0) && (tensor->view_src == nullptr)) {
-        rpc_msg_init_tensor_req request;
-
-        request.tensor = serialize_tensor(tensor);
-
-        bool status = send_rpc_cmd(ctx->sock, RPC_CMD_INIT_TENSOR, &request, sizeof(request), nullptr, 0);
-        GGML_ASSERT(status);
+GGML_CALL static void ggml_backend_rpc_buffer_init_tensor(ggml_backend_buffer_t buffer, ggml_tensor * tensor) {
+    UNUSED(buffer);
+    if (ggml_is_quantized(tensor->type)) {
+        // TODO: this check is due to MATRIX_ROW_PADDING in CUDA and should be generalized
+        GGML_ASSERT(tensor->ne[0] % 512 == 0 && "unsupported quantized tensor");
     }
 }
 
-static void ggml_backend_rpc_buffer_set_tensor(ggml_backend_buffer_t buffer, ggml_tensor* tensor, const void* data, size_t offset, size_t size) {
-    ggml_backend_rpc_buffer_context* ctx = (ggml_backend_rpc_buffer_context*)buffer->context;
-    rpc_tensor rpc_tensor = serialize_tensor(tensor);
-    if (size > HASH_THRESHOLD) {
-        // input serialization format: | rpc_tensor | offset (8 bytes) | hash (8 bytes)
-        size_t input_size = sizeof(rpc_tensor) + sizeof(uint64_t) + sizeof(uint64_t);
-        std::vector<uint8_t> input(input_size, 0);
-        uint64_t hash = fnv_hash((const uint8_t*)data, size);
-        memcpy(input.data(), &rpc_tensor, sizeof(rpc_tensor));
-        memcpy(input.data() + sizeof(rpc_tensor), &offset, sizeof(offset));
-        memcpy(input.data() + sizeof(rpc_tensor) + sizeof(offset), &hash, sizeof(hash));
-        rpc_msg_set_tensor_hash_rsp response;
-        bool status = send_rpc_cmd(ctx->sock, RPC_CMD_SET_TENSOR_HASH, input.data(), input.size(), &response, sizeof(response));
-        GGML_ASSERT(status);
-        if (response.result) {
-            // the server has the same data, no need to send it
-            return;
-        }
-    }
-    // input serialization format: | rpc_tensor | offset (8 bytes) | data (size bytes)
+GGML_CALL static void ggml_backend_rpc_buffer_set_tensor(ggml_backend_buffer_t buffer, ggml_tensor * tensor, const void * data, size_t offset, size_t size) {
+    ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
+    // input serialization format: | rpc_tensor | offset (8 bytes) | data (size bytes) |
     size_t input_size = sizeof(rpc_tensor) + sizeof(uint64_t) + size;
     std::vector<uint8_t> input(input_size, 0);
+    rpc_tensor rpc_tensor = serialize_tensor(tensor);
     memcpy(input.data(), &rpc_tensor, sizeof(rpc_tensor));
     memcpy(input.data() + sizeof(rpc_tensor), &offset, sizeof(offset));
     memcpy(input.data() + sizeof(rpc_tensor) + sizeof(offset), data, size);
-    bool status = send_rpc_cmd(ctx->sock, RPC_CMD_SET_TENSOR, input.data(), input.size());
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(ctx->sock, SET_TENSOR, input, output);
     GGML_ASSERT(status);
 }
 
-
-static void ggml_backend_rpc_buffer_get_tensor(ggml_backend_buffer_t buffer, const ggml_tensor* tensor, void* data, size_t offset, size_t size) {
-    ggml_backend_rpc_buffer_context* ctx = (ggml_backend_rpc_buffer_context*)buffer->context;
-    rpc_msg_get_tensor_req request;
-    request.tensor = serialize_tensor(tensor);
-    request.offset = offset;
-    request.size = size;
-    bool status = send_rpc_cmd(ctx->sock, RPC_CMD_GET_TENSOR, &request, sizeof(request), data, size);
+GGML_CALL static void ggml_backend_rpc_buffer_get_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * tensor, void * data, size_t offset, size_t size) {
+    ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
+    // input serialization format: | rpc_tensor | offset (8 bytes) | size (8 bytes) |
+    int input_size = sizeof(rpc_tensor) + 2*sizeof(uint64_t);
+    std::vector<uint8_t> input(input_size, 0);
+    rpc_tensor rpc_tensor = serialize_tensor(tensor);
+    memcpy(input.data(), &rpc_tensor, sizeof(rpc_tensor));
+    memcpy(input.data() + sizeof(rpc_tensor), &offset, sizeof(offset));
+    memcpy(input.data() + sizeof(rpc_tensor) + sizeof(offset), &size, sizeof(size));
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(ctx->sock, GET_TENSOR, input, output);
     GGML_ASSERT(status);
+    GGML_ASSERT(output.size() == size);
+    // output serialization format: | data (size bytes) |
+    memcpy(data, output.data(), size);
 }
 
-
-static bool ggml_backend_rpc_buffer_cpy_tensor(ggml_backend_buffer_t buffer, const ggml_tensor* src, ggml_tensor* dst) {
+GGML_CALL static bool ggml_backend_rpc_buffer_cpy_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * src, ggml_tensor * dst) {
     // check if src and dst are on the same server
     ggml_backend_buffer_t src_buffer = src->buffer;
-    ggml_backend_rpc_buffer_context* src_ctx = (ggml_backend_rpc_buffer_context*)src_buffer->context;
+    ggml_backend_rpc_buffer_context * src_ctx = (ggml_backend_rpc_buffer_context *)src_buffer->context;
     ggml_backend_buffer_t dst_buffer = dst->buffer;
-    ggml_backend_rpc_buffer_context* dst_ctx = (ggml_backend_rpc_buffer_context*)dst_buffer->context;
+    ggml_backend_rpc_buffer_context * dst_ctx = (ggml_backend_rpc_buffer_context *)dst_buffer->context;
     if (src_ctx->sock != dst_ctx->sock) {
         return false;
     }
-    ggml_backend_rpc_buffer_context* ctx = (ggml_backend_rpc_buffer_context*)buffer->context;
-    rpc_msg_copy_tensor_req request;
-    request.src = serialize_tensor(src);
-    request.dst = serialize_tensor(dst);
-    rpc_msg_copy_tensor_rsp response;
-    bool status = send_rpc_cmd(ctx->sock, RPC_CMD_COPY_TENSOR, &request, sizeof(request), &response, sizeof(response));
+    ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
+    // input serialization format: | rpc_tensor src | rpc_tensor dst |
+    int input_size = 2*sizeof(rpc_tensor);
+    std::vector<uint8_t> input(input_size, 0);
+    rpc_tensor rpc_src = serialize_tensor(src);
+    rpc_tensor rpc_dst = serialize_tensor(dst);
+    memcpy(input.data(), &rpc_src, sizeof(rpc_src));
+    memcpy(input.data() + sizeof(rpc_src), &rpc_dst, sizeof(rpc_dst));
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(ctx->sock, COPY_TENSOR, input, output);
     GGML_ASSERT(status);
-    return response.result;
+    // output serialization format: | result (1 byte) |
+    GGML_ASSERT(output.size() == 1);
+    return output[0];
 }
 
-static void ggml_backend_rpc_buffer_clear(ggml_backend_buffer_t buffer, uint8_t value) {
-    ggml_backend_rpc_buffer_context* ctx = (ggml_backend_rpc_buffer_context*)buffer->context;
-    rpc_msg_buffer_clear_req request = { ctx->remote_ptr, value };
-    bool status = send_rpc_cmd(ctx->sock, RPC_CMD_BUFFER_CLEAR, &request, sizeof(request), nullptr, 0);
+GGML_CALL static void ggml_backend_rpc_buffer_clear(ggml_backend_buffer_t buffer, uint8_t value) {
+    ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
+    // serialization format: | bufptr (8 bytes) | value (1 byte) |
+    int input_size = sizeof(uint64_t) + sizeof(uint8_t);
+    std::vector<uint8_t> input(input_size, 0);
+    memcpy(input.data(), &ctx->remote_ptr, sizeof(ctx->remote_ptr));
+    memcpy(input.data() + sizeof(ctx->remote_ptr), &value, sizeof(value));
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(ctx->sock, BUFFER_CLEAR, input, output);
     GGML_ASSERT(status);
 }
 
-
 static ggml_backend_buffer_i ggml_backend_rpc_buffer_interface = {
     /* .get_name        = */ ggml_backend_rpc_buffer_get_name,
     /* .free_buffer     = */ ggml_backend_rpc_buffer_free_buffer,
@@ -643,45 +480,62 @@ GGML_CALL static const char * ggml_backend_rpc_buffer_type_name(ggml_backend_buf
     return buft_ctx->name.c_str();
 }
 
-static ggml_backend_buffer_t ggml_backend_rpc_buffer_type_alloc_buffer(ggml_backend_buffer_type_t buft, size_t size) {
-    ggml_backend_rpc_buffer_type_context* buft_ctx = (ggml_backend_rpc_buffer_type_context*)buft->context;
-    rpc_msg_alloc_buffer_req request = { size };
-    rpc_msg_alloc_buffer_rsp response;
+GGML_CALL static ggml_backend_buffer_t ggml_backend_rpc_buffer_type_alloc_buffer(ggml_backend_buffer_type_t buft, size_t size) {
+    ggml_backend_rpc_buffer_type_context * buft_ctx = (ggml_backend_rpc_buffer_type_context *)buft->context;
+    // input serialization format: | size (8 bytes) |
+    int input_size = sizeof(uint64_t);
+    std::vector<uint8_t> input(input_size, 0);
+    memcpy(input.data(), &size, sizeof(size));
+    std::vector<uint8_t> output;
     auto sock = get_socket(buft_ctx->endpoint);
-    std::string name= "RPC[" + std::string(buft_ctx->endpoint) + "]";
-    bool status = send_rpc_cmd(sock, RPC_CMD_ALLOC_BUFFER, &request, sizeof(request), &response, sizeof(response));
+    bool status = send_rpc_cmd(sock, ALLOC_BUFFER, input, output);
     GGML_ASSERT(status);
-    if (response.remote_ptr != 0) {
+    GGML_ASSERT(output.size() == 2*sizeof(uint64_t));
+    // output serialization format: | remote_ptr (8 bytes) | remote_size (8 bytes) |
+    uint64_t remote_ptr;
+    memcpy(&remote_ptr, output.data(), sizeof(remote_ptr));
+    size_t remote_size;
+    memcpy(&remote_size, output.data() + sizeof(uint64_t), sizeof(remote_size));
+    if (remote_ptr != 0) {
         ggml_backend_buffer_t buffer = ggml_backend_buffer_init(buft,
             ggml_backend_rpc_buffer_interface,
-            new ggml_backend_rpc_buffer_context{ sock, nullptr, response.remote_ptr, name },
-            response.remote_size);
+            new ggml_backend_rpc_buffer_context{sock, {}, remote_ptr, "RPC[" + std::string(buft_ctx->endpoint) + "]"},
+            remote_size);
         return buffer;
-    }
-    else {
+    } else {
         return nullptr;
     }
 }
 
-
-static size_t get_alignment(const std::shared_ptr<socket_t>& sock) {
-    rpc_msg_get_alignment_rsp response;
-    bool status = send_rpc_cmd(sock, RPC_CMD_GET_ALIGNMENT, nullptr, 0, &response, sizeof(response));
+static size_t get_alignment(const std::shared_ptr<socket_t> & sock) {
+    // input serialization format: | 0 bytes |
+    std::vector<uint8_t> input;
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(sock, GET_ALIGNMENT, input, output);
     GGML_ASSERT(status);
-    return response.alignment;
+    GGML_ASSERT(output.size() == sizeof(uint64_t));
+    // output serialization format: | alignment (8 bytes) |
+    uint64_t alignment;
+    memcpy(&alignment, output.data(), sizeof(alignment));
+    return alignment;
 }
 
-
 GGML_CALL static size_t ggml_backend_rpc_buffer_type_get_alignment(ggml_backend_buffer_type_t buft) {
     ggml_backend_rpc_buffer_type_context * buft_ctx = (ggml_backend_rpc_buffer_type_context *)buft->context;
     return buft_ctx->alignment;
 }
 
-static size_t get_max_size(const std::shared_ptr<socket_t>& sock) {
-    rpc_msg_get_max_size_rsp response;
-    bool status = send_rpc_cmd(sock, RPC_CMD_GET_MAX_SIZE, nullptr, 0, &response, sizeof(response));
+static size_t get_max_size(const std::shared_ptr<socket_t> & sock) {
+    // input serialization format: | 0 bytes |
+    std::vector<uint8_t> input;
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(sock, GET_MAX_SIZE, input, output);
     GGML_ASSERT(status);
-    return response.max_size;
+    GGML_ASSERT(output.size() == sizeof(uint64_t));
+    // output serialization format: | max_size (8 bytes) |
+    uint64_t max_size;
+    memcpy(&max_size, output.data(), sizeof(max_size));
+    return max_size;
 }
 
 GGML_CALL static size_t ggml_backend_rpc_get_max_size(ggml_backend_buffer_type_t buft) {
@@ -689,29 +543,11 @@ GGML_CALL static size_t ggml_backend_rpc_get_max_size(ggml_backend_buffer_type_t
     return buft_ctx->max_size;
 }
 
-GGML_CALL static size_t ggml_backend_rpc_buffer_type_get_alloc_size(ggml_backend_buffer_type_t buft, const ggml_tensor* tensor) {
-    // See comments in init_tensor.
-    if (ggml_is_quantized(tensor->type) && (tensor->ne[0] % 512 != 0) && (tensor->view_src == nullptr)) {
-        ggml_backend_rpc_buffer_type_context* buft_ctx = (ggml_backend_rpc_buffer_type_context*)buft->context;
-        auto sock = get_socket(buft_ctx->endpoint);
-
-        rpc_msg_get_alloc_size_req request;
-
-        request.tensor = serialize_tensor(tensor);
-
-        rpc_msg_get_alloc_size_rsp response;
-        bool status = send_rpc_cmd(sock, RPC_CMD_GET_ALLOC_SIZE, &request, sizeof(request), &response, sizeof(response));
-        GGML_ASSERT(status);
-
-        return response.alloc_size;
-    }
-    else {
-        return ggml_nbytes(tensor);
-    }
+GGML_CALL static size_t ggml_backend_rpc_buffer_type_get_alloc_size(ggml_backend_buffer_type_t buft, const ggml_tensor * tensor) {
+    UNUSED(buft);
+    return ggml_nbytes(tensor);
 }
 
-
-
 static ggml_backend_buffer_type_i ggml_backend_rpc_buffer_type_interface = {
     /* .get_name         = */ ggml_backend_rpc_buffer_type_name,
     /* .alloc_buffer     = */ ggml_backend_rpc_buffer_type_alloc_buffer,
@@ -780,15 +616,16 @@ static void serialize_graph(const ggml_cgraph * cgraph, std::vector<uint8_t> & o
     memcpy(out_tensors, tensors.data(), n_tensors * sizeof(rpc_tensor));
 }
 
-static enum ggml_status ggml_backend_rpc_graph_compute(ggml_backend_t backend, ggml_cgraph* cgraph) {
-    ggml_backend_rpc_context* rpc_ctx = (ggml_backend_rpc_context*)backend->context;
+GGML_CALL static enum ggml_status ggml_backend_rpc_graph_compute(ggml_backend_t backend, ggml_cgraph * cgraph) {
+    ggml_backend_rpc_context * rpc_ctx = (ggml_backend_rpc_context *)backend->context;
     std::vector<uint8_t> input;
     serialize_graph(cgraph, input);
-    rpc_msg_graph_compute_rsp response;
+    std::vector<uint8_t> output;
     auto sock = get_socket(rpc_ctx->endpoint);
-    bool status = send_rpc_cmd(sock, RPC_CMD_GRAPH_COMPUTE, input.data(), input.size(), &response, sizeof(response));
+    bool status = send_rpc_cmd(sock, GRAPH_COMPUTE, input, output);
     GGML_ASSERT(status);
-    return (enum ggml_status)response.result;
+    GGML_ASSERT(output.size() == 1);
+    return (enum ggml_status)output[0];
 }
 
 GGML_CALL static bool ggml_backend_rpc_supports_op(ggml_backend_t backend, const ggml_tensor * op) {
@@ -799,7 +636,7 @@ GGML_CALL static bool ggml_backend_rpc_supports_op(ggml_backend_t backend, const
 }
 
 GGML_CALL static bool ggml_backend_rpc_supports_buft(ggml_backend_t backend, ggml_backend_buffer_type_t buft) {
-    if (!buft || buft->iface.get_name != ggml_backend_rpc_buffer_type_name) {
+    if (buft->iface.get_name != ggml_backend_rpc_buffer_type_name) {
         return false;
     }
     ggml_backend_rpc_buffer_type_context * buft_ctx = (ggml_backend_rpc_buffer_type_context *)buft->context;
@@ -841,7 +678,6 @@ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const
     }
     auto sock = get_socket(endpoint);
     if (sock == nullptr) {
-        fprintf(stderr, "Failed to connect to %s\n", endpoint);
         return nullptr;
     }
     size_t alignment = get_alignment(sock);
@@ -852,7 +688,7 @@ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const
         /* .alignment = */ alignment,
         /* .max_size  = */ max_size
     };
-    rpc_server_map[endpoint] = "RPC[" + std::string(endpoint) + "]";
+
     ggml_backend_buffer_type_t buft = new ggml_backend_buffer_type {
         /* .iface   = */ ggml_backend_rpc_buffer_type_interface,
         /* .context = */ buft_ctx
@@ -861,31 +697,6 @@ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const
     return buft;
 }
 
-// backend registry
-GGML_CALL static ggml_backend_t ggml_backend_reg_rpc_init(const char* params, void* user_data) {
-    ggml_backend_t cuda_backend = ggml_backend_rpc_init((const char*)user_data);
-    return cuda_backend;
-
-    GGML_UNUSED(params);
-}
-
-
-extern "C" GGML_CALL int ggml_backend_rpc_reg_devices();
-
-GGML_CALL int ggml_backend_rpc_reg_devices() {
-    //static std::unordered_map<std::string, ggml_backend_buffer_type_t> buft_map;
-    int device_count = (int)rpc_server_map.size();
-    int i = 0;
-    for (auto& it : rpc_server_map)
-    {
-        std::string endpoint =  it.first;
-        auto name = "RPC[" + std::string(endpoint) + "]";
-        ggml_backend_register(name.c_str(), ggml_backend_reg_rpc_init, ggml_backend_rpc_buffer_type(endpoint.c_str()), &(endpoint));
-        i++;
-    }
-    return device_count;
-}
-
 GGML_CALL ggml_backend_t ggml_backend_rpc_init(const char * endpoint) {
     ggml_backend_rpc_context * ctx = new ggml_backend_rpc_context {
         /* .endpoint  = */ endpoint,
@@ -904,12 +715,20 @@ GGML_API GGML_CALL bool ggml_backend_is_rpc(ggml_backend_t backend) {
     return backend != NULL && ggml_guid_matches(backend->guid, ggml_backend_rpc_guid());
 }
 
-static void get_device_memory(const std::shared_ptr<socket_t>& sock, size_t* free, size_t* total) {
-    rpc_msg_get_device_memory_rsp response;
-    bool status = send_rpc_cmd(sock, RPC_CMD_GET_DEVICE_MEMORY, nullptr, 0, &response, sizeof(response));
+static void get_device_memory(const std::shared_ptr<socket_t> & sock, size_t * free, size_t * total) {
+    // input serialization format: | 0 bytes |
+    std::vector<uint8_t> input;
+    std::vector<uint8_t> output;
+    bool status = send_rpc_cmd(sock, GET_DEVICE_MEMORY, input, output);
     GGML_ASSERT(status);
-    *free = response.free_mem;
-    *total = response.total_mem;
+    GGML_ASSERT(output.size() == 2*sizeof(uint64_t));
+    // output serialization format: | free (8 bytes) | total (8 bytes) |
+    uint64_t free_mem;
+    memcpy(&free_mem, output.data(), sizeof(free_mem));
+    uint64_t total_mem;
+    memcpy(&total_mem, output.data() + sizeof(uint64_t), sizeof(total_mem));
+    *free = free_mem;
+    *total = total_mem;
 }
 
 GGML_API GGML_CALL void ggml_backend_rpc_get_device_memory(const char * endpoint, size_t * free, size_t * total) {
@@ -926,27 +745,21 @@ GGML_API GGML_CALL void ggml_backend_rpc_get_device_memory(const char * endpoint
 
 class rpc_server {
 public:
-    rpc_server(ggml_backend_t backend, const char* cache_dir)
-        : backend(backend), cache_dir(cache_dir) {
-    }
+    rpc_server(ggml_backend_t backend) : backend(backend) {}
     ~rpc_server();
-    void hello(rpc_msg_hello_rsp& response);
-    void alloc_buffer(const rpc_msg_alloc_buffer_req& request, rpc_msg_alloc_buffer_rsp& response);
-    void get_alignment(rpc_msg_get_alignment_rsp& response);
-    void get_max_size(rpc_msg_get_max_size_rsp& response);
-    bool buffer_get_base(const rpc_msg_buffer_get_base_req& request, rpc_msg_buffer_get_base_rsp& response);
-    bool free_buffer(const rpc_msg_free_buffer_req& request);
-    bool buffer_clear(const rpc_msg_buffer_clear_req& request);
-    bool set_tensor(const std::vector<uint8_t>& input);
-    bool set_tensor_hash(const std::vector<uint8_t>& input, rpc_msg_set_tensor_hash_rsp& response);
-    bool get_tensor(const rpc_msg_get_tensor_req& request, std::vector<uint8_t>& response);
-    bool copy_tensor(const rpc_msg_copy_tensor_req& request, rpc_msg_copy_tensor_rsp& response);
-    bool graph_compute(const std::vector<uint8_t>& input, rpc_msg_graph_compute_rsp& response);
-    bool init_tensor(const rpc_msg_init_tensor_req& request);
-    bool get_alloc_size(const rpc_msg_get_alloc_size_req& request, rpc_msg_get_alloc_size_rsp& response);
+
+    bool alloc_buffer(const std::vector<uint8_t> & input, std::vector<uint8_t> & output);
+    void get_alignment(std::vector<uint8_t> & output);
+    void get_max_size(std::vector<uint8_t> & output);
+    bool buffer_get_base(const std::vector<uint8_t> & input, std::vector<uint8_t> & output);
+    bool free_buffer(const std::vector<uint8_t> & input);
+    bool buffer_clear(const std::vector<uint8_t> & input);
+    bool set_tensor(const std::vector<uint8_t> & input);
+    bool get_tensor(const std::vector<uint8_t> & input, std::vector<uint8_t> & output);
+    bool copy_tensor(const std::vector<uint8_t> & input, std::vector<uint8_t> & output);
+    bool graph_compute(const std::vector<uint8_t> & input, std::vector<uint8_t> & output);
 
 private:
-    bool get_cached_file(uint64_t hash, std::vector<uint8_t>& data);
     ggml_tensor * deserialize_tensor(struct ggml_context * ctx, const rpc_tensor * tensor);
     ggml_tensor * create_node(uint64_t id,
                               struct ggml_context * ctx,
@@ -955,93 +768,85 @@ private:
 
 
     ggml_backend_t backend;
-    const char* cache_dir;
     std::unordered_set<ggml_backend_buffer_t> buffers;
 };
 
-void rpc_server::hello(rpc_msg_hello_rsp& response) {
-    response.major = RPC_PROTO_MAJOR_VERSION;
-    response.minor = RPC_PROTO_MINOR_VERSION;
-    response.patch = RPC_PROTO_PATCH_VERSION;
-    GGML_PRINT_DEBUG("[%s] version: %d.%d.%d\n", __func__, response.major, response.minor, response.patch);
-}
-
-bool rpc_server::get_alloc_size(const rpc_msg_get_alloc_size_req& request, rpc_msg_get_alloc_size_rsp& response) {
-    ggml_backend_buffer_type_t buft;
-    struct ggml_init_params params {
-        /*.mem_size   =*/ ggml_tensor_overhead(),
-            /*.mem_buffer =*/ NULL,
-            /*.no_alloc   =*/ true,
-    };
-
-    struct ggml_context* ctx = ggml_init(params);
-    ggml_tensor* tensor = deserialize_tensor(ctx, &request.tensor);
-
-    if (tensor == nullptr) {
-        GGML_ABORT("Null tensor pointer passed to server get_alloc_size function.\n");
-        ggml_free(ctx);
+bool rpc_server::alloc_buffer(const std::vector<uint8_t> & input, std::vector<uint8_t> & output) {
+    // input serialization format: | size (8 bytes) |
+    if (input.size() != sizeof(uint64_t)) {
         return false;
     }
-
-    if (tensor->buffer == nullptr) {
-        //No buffer allocated.
-        buft = ggml_backend_get_default_buffer_type(backend);
-    }
-    else {
-        buft = tensor->buffer->buft;
-    }
-
-    response.alloc_size = ggml_backend_buft_get_alloc_size(buft, tensor);
-
-    ggml_free(ctx);
-    return true;
-}
-void rpc_server::alloc_buffer(const rpc_msg_alloc_buffer_req& request, rpc_msg_alloc_buffer_rsp& response) {
+    uint64_t size;
+    memcpy(&size, input.data(), sizeof(size));
     ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backend);
-    ggml_backend_buffer_t buffer = ggml_backend_buft_alloc_buffer(buft, request.size);
-    response.remote_ptr = 0;
-    response.remote_size = 0;
+    ggml_backend_buffer_t buffer = ggml_backend_buft_alloc_buffer(buft, size);
+    uint64_t remote_ptr = 0;
+    uint64_t remote_size = 0;
     if (buffer != nullptr) {
-        response.remote_ptr = reinterpret_cast<uint64_t>(buffer);
-        response.remote_size = buffer->size;
-        GGML_PRINT_DEBUG("[%s] size: %" PRIu64 " -> remote_ptr: %" PRIx64 ", remote_size: %" PRIu64 "\n", __func__, request.size, response.remote_ptr, response.remote_size);
+        remote_ptr = reinterpret_cast<uint64_t>(buffer);
+        remote_size = buffer->size;
+        GGML_PRINT_DEBUG("[%s] size: %" PRIu64 " -> remote_ptr: %" PRIx64 ", remote_size: %" PRIu64 "\n", __func__, size, remote_ptr, remote_size);
         buffers.insert(buffer);
+    } else {
+        GGML_PRINT_DEBUG("[%s] size: %" PRIu64 " -> failed\n", __func__, size);
     }
-    else {
-        GGML_ABORT("[%s] size: %" PRIu64 " -> failed\n", __func__, request.size);
-    }
+    // output serialization format: | remote_ptr (8 bytes) | remote_size (8 bytes) |
+    output.resize(2*sizeof(uint64_t), 0);
+    memcpy(output.data(), &remote_ptr, sizeof(remote_ptr));
+    memcpy(output.data() + sizeof(uint64_t), &remote_size, sizeof(remote_size));
+    return true;
 }
-void rpc_server::get_alignment(rpc_msg_get_alignment_rsp& response) {
+
+void rpc_server::get_alignment(std::vector<uint8_t> & output) {
     ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backend);
     size_t alignment = ggml_backend_buft_get_alignment(buft);
     GGML_PRINT_DEBUG("[%s] alignment: %lu\n", __func__, alignment);
-    response.alignment = alignment;
+    // output serialization format: | alignment (8 bytes) |
+    output.resize(sizeof(uint64_t), 0);
+    memcpy(output.data(), &alignment, sizeof(alignment));
 }
 
-void rpc_server::get_max_size(rpc_msg_get_max_size_rsp& response) {
+void rpc_server::get_max_size(std::vector<uint8_t> & output) {
     ggml_backend_buffer_type_t buft = ggml_backend_get_default_buffer_type(backend);
     size_t max_size = ggml_backend_buft_get_max_size(buft);
     GGML_PRINT_DEBUG("[%s] max_size: %lu\n", __func__, max_size);
-    response.max_size = max_size;
+    // output serialization format: | max_size (8 bytes) |
+    output.resize(sizeof(uint64_t), 0);
+    memcpy(output.data(), &max_size, sizeof(max_size));
 }
 
-bool rpc_server::buffer_get_base(const rpc_msg_buffer_get_base_req& request, rpc_msg_buffer_get_base_rsp& response) {
-    GGML_PRINT_DEBUG("[%s] remote_ptr: %" PRIx64 "\n", __func__, request.remote_ptr);
-    ggml_backend_buffer_t buffer = reinterpret_cast<ggml_backend_buffer_t>(request.remote_ptr);
+bool rpc_server::buffer_get_base(const std::vector<uint8_t> & input, std::vector<uint8_t> & output) {
+    // input serialization format: | remote_ptr (8 bytes) |
+    if (input.size() != sizeof(uint64_t)) {
+        return false;
+    }
+    uint64_t remote_ptr;
+    memcpy(&remote_ptr, input.data(), sizeof(remote_ptr));
+    GGML_PRINT_DEBUG("[%s] remote_ptr: %" PRIx64 "\n", __func__, remote_ptr);
+    ggml_backend_buffer_t buffer = reinterpret_cast<ggml_backend_buffer_t>(remote_ptr);
     if (buffers.find(buffer) == buffers.end()) {
-        GGML_ABORT("[%s] buffer not found\n", __func__);
+        GGML_PRINT_DEBUG("[%s] buffer not found\n", __func__);
         return false;
     }
-    void* base = ggml_backend_buffer_get_base(buffer);
-    response.base_ptr = reinterpret_cast<uint64_t>(base);
+    void * base = ggml_backend_buffer_get_base(buffer);
+    // output serialization format: | base_ptr (8 bytes) |
+    uint64_t base_ptr = reinterpret_cast<uint64_t>(base);
+    output.resize(sizeof(uint64_t), 0);
+    memcpy(output.data(), &base_ptr, sizeof(base_ptr));
     return true;
 }
 
-bool rpc_server::free_buffer(const rpc_msg_free_buffer_req& request) {
-    GGML_PRINT_DEBUG("[%s] remote_ptr: %" PRIx64 "\n", __func__, request.remote_ptr);
-    ggml_backend_buffer_t buffer = reinterpret_cast<ggml_backend_buffer_t>(request.remote_ptr);
+bool rpc_server::free_buffer(const std::vector<uint8_t> & input) {
+    // input serialization format: | remote_ptr (8 bytes) |
+    if (input.size() != sizeof(uint64_t)) {
+        return false;
+    }
+    uint64_t remote_ptr;
+    memcpy(&remote_ptr, input.data(), sizeof(remote_ptr));
+    GGML_PRINT_DEBUG("[%s] remote_ptr: %" PRIx64 "\n", __func__, remote_ptr);
+    ggml_backend_buffer_t buffer = reinterpret_cast<ggml_backend_buffer_t>(remote_ptr);
     if (buffers.find(buffer) == buffers.end()) {
-        GGML_ABORT("[%s] buffer not found\n", __func__);
+        GGML_PRINT_DEBUG("[%s] buffer not found\n", __func__);
         return false;
     }
     ggml_backend_buffer_free(buffer);
@@ -1049,49 +854,42 @@ bool rpc_server::free_buffer(const rpc_msg_free_buffer_req& request) {
     return true;
 }
 
-bool rpc_server::buffer_clear(const rpc_msg_buffer_clear_req& request) {
-    GGML_PRINT_DEBUG("[%s] remote_ptr: %" PRIx64 ", value: %u\n", __func__, request.remote_ptr, request.value);
-    ggml_backend_buffer_t buffer = reinterpret_cast<ggml_backend_buffer_t>(request.remote_ptr);
+bool rpc_server::buffer_clear(const std::vector<uint8_t> & input) {
+    // input serialization format: | remote_ptr (8 bytes) | value (1 byte) |
+    if (input.size() != sizeof(uint64_t) + sizeof(uint8_t)) {
+        return false;
+    }
+    uint64_t remote_ptr;
+    memcpy(&remote_ptr, input.data(), sizeof(remote_ptr));
+    uint8_t value;
+    memcpy(&value, input.data() + sizeof(uint64_t), sizeof(value));
+    GGML_PRINT_DEBUG("[%s] remote_ptr: %" PRIx64 ", value: %u\n", __func__, remote_ptr, value);
+    ggml_backend_buffer_t buffer = reinterpret_cast<ggml_backend_buffer_t>(remote_ptr);
     if (buffers.find(buffer) == buffers.end()) {
-        GGML_ABORT("[%s] buffer not found\n", __func__);
+        GGML_PRINT_DEBUG("[%s] buffer not found\n", __func__);
         return false;
     }
-    ggml_backend_buffer_clear(buffer, request.value);
+    ggml_backend_buffer_clear(buffer, value);
     return true;
 }
 
 ggml_tensor * rpc_server::deserialize_tensor(struct ggml_context * ctx, const rpc_tensor * tensor) {
-    // Validate tensor type before using it
-    if (tensor->type >= GGML_TYPE_COUNT) {
-        GGML_PRINT_DEBUG("[%s] invalid tensor type received: %u\n", __func__, tensor->type);
-        return nullptr;
-    }
-
     ggml_tensor * result = ggml_new_tensor_4d(ctx, (ggml_type) tensor->type,
         tensor->ne[0], tensor->ne[1], tensor->ne[2], tensor->ne[3]);
-
-    // ggml_new_tensor_4d might fail if dimensions are invalid, although less likely to crash than invalid type
-    if (result == nullptr) {
-        GGML_PRINT_DEBUG("[%s] ggml_new_tensor_4d failed for type %u\\n", __func__, tensor->type);
-        return nullptr;
-    }
-
     for (uint32_t i = 0; i < GGML_MAX_DIMS; i++) {
         result->nb[i] = tensor->nb[i];
     }
     result->buffer = reinterpret_cast<ggml_backend_buffer_t>(tensor->buffer);
     if (result->buffer && buffers.find(result->buffer) == buffers.end()) {
-        result->buffer = nullptr;
+        return nullptr;
     }
 
-    if (result->buffer) {
-        // require that the tensor data does not go beyond the buffer end
-        uint64_t tensor_size = (uint64_t) ggml_nbytes(result);
-        uint64_t buffer_start = (uint64_t) ggml_backend_buffer_get_base(result->buffer);
-        uint64_t buffer_size = (uint64_t) ggml_backend_buffer_get_size(result->buffer);
-        GGML_ASSERT(tensor->data + tensor_size >= tensor->data); // check for overflow
-        GGML_ASSERT(tensor->data >= buffer_start && tensor->data + tensor_size <= buffer_start + buffer_size);
-    }
+    // require that the tensor data does not go beyond the buffer end
+    uint64_t tensor_size = (uint64_t) ggml_nbytes(result);
+    uint64_t buffer_start = (uint64_t) ggml_backend_buffer_get_base(result->buffer);
+    uint64_t buffer_size = (uint64_t) ggml_backend_buffer_get_size(result->buffer);
+    GGML_ASSERT(tensor->data + tensor_size >= tensor->data); // check for overflow
+    GGML_ASSERT(tensor->data >= buffer_start && tensor->data + tensor_size <= buffer_start + buffer_size);
 
     result->op = (ggml_op) tensor->op;
     for (uint32_t i = 0; i < GGML_MAX_OP_PARAMS / sizeof(int32_t); i++) {
@@ -1104,25 +902,25 @@ ggml_tensor * rpc_server::deserialize_tensor(struct ggml_context * ctx, const rp
 }
 
 
-bool rpc_server::set_tensor(const std::vector<uint8_t>& input) {
+bool rpc_server::set_tensor(const std::vector<uint8_t> & input) {
     // serialization format: | rpc_tensor | offset (8 bytes) | data (size bytes) |
     if (input.size() < sizeof(rpc_tensor) + sizeof(uint64_t)) {
         return false;
     }
-    const rpc_tensor* in_tensor = (const rpc_tensor*)input.data();
+    const rpc_tensor * in_tensor = (const rpc_tensor *)input.data();
     uint64_t offset;
     memcpy(&offset, input.data() + sizeof(rpc_tensor), sizeof(offset));
     const size_t size = input.size() - sizeof(rpc_tensor) - sizeof(offset);
 
     struct ggml_init_params params {
         /*.mem_size   =*/ ggml_tensor_overhead(),
-            /*.mem_buffer =*/ NULL,
-            /*.no_alloc   =*/ true,
+        /*.mem_buffer =*/ NULL,
+        /*.no_alloc   =*/ true,
     };
-    struct ggml_context* ctx = ggml_init(params);
-    ggml_tensor* tensor = deserialize_tensor(ctx, in_tensor);
+    struct ggml_context * ctx = ggml_init(params);
+    ggml_tensor * tensor = deserialize_tensor(ctx, in_tensor);
     if (tensor == nullptr) {
-        GGML_ABORT("[%s] error deserializing tensor\n", __func__);
+        GGML_PRINT_DEBUG("[%s] error deserializing tensor\n", __func__);
         ggml_free(ctx);
         return false;
     }
@@ -1130,262 +928,117 @@ bool rpc_server::set_tensor(const std::vector<uint8_t>& input) {
 
     // sanitize tensor->data
     {
-        const size_t p0 = (size_t)ggml_backend_buffer_get_base(tensor->buffer);
+        const size_t p0 = (size_t) ggml_backend_buffer_get_base(tensor->buffer);
         const size_t p1 = p0 + ggml_backend_buffer_get_size(tensor->buffer);
 
-        if (in_tensor->data + offset < p0 || in_tensor->data + offset >= p1 || size >(p1 - in_tensor->data - offset)) {
-            GGML_PRINT_DEBUG("[%s] tensor data region (data=0x%" PRIx64 ", offset=%" PRIu64 ", size=%zu) out of buffer bounds [0x%zx, 0x%zx)\n",
-                           __func__, in_tensor->data, offset, size, p0, p1);
-            return false;
+        if (in_tensor->data + offset < p0 || in_tensor->data + offset >= p1 || size > (p1 - in_tensor->data - offset)) {
+            GGML_ABORT("[%s] tensor->data out of bounds\n", __func__);
         }
     }
 
-    const void* data = input.data() + sizeof(rpc_tensor) + sizeof(offset);
-    if (cache_dir && size > HASH_THRESHOLD) {
-        uint64_t hash = fnv_hash((const uint8_t*)data, size);
-        char hash_str[17];
-        snprintf(hash_str, sizeof(hash_str), "%016" PRIx64, hash);
-        // save to cache_dir/hash_str
-        fs::path cache_file = fs::path(cache_dir) / hash_str;
-        std::ofstream ofs(cache_file, std::ios::binary);
-        ofs.write((const char*)data, size);
-        printf("[%s] saved to '%s'\n", __func__, cache_file.c_str());
-    }
+    const void * data = input.data() + sizeof(rpc_tensor) + sizeof(offset);
     ggml_backend_tensor_set(tensor, data, offset, size);
     ggml_free(ctx);
     return true;
 }
 
-
-bool rpc_server::get_cached_file(uint64_t hash, std::vector<uint8_t>& data) {
-    if (!cache_dir) {
+bool rpc_server::get_tensor(const std::vector<uint8_t> & input, std::vector<uint8_t> & output) {
+    // serialization format: | rpc_tensor | offset (8 bytes) | size (8 bytes) |
+    if (input.size() != sizeof(rpc_tensor) + 2*sizeof(uint64_t)) {
         return false;
     }
-    char hash_str[17];
-    snprintf(hash_str, sizeof(hash_str), "%016" PRIx64, hash);
-    fs::path cache_file = fs::path(cache_dir) / hash_str;
-    if (!fs::exists(cache_file)) {
-        return false;
-    }
-    std::ifstream ifs(cache_file, std::ios::binary);
-    ifs.seekg(0, std::ios::end);
-    size_t size = ifs.tellg();
-    ifs.seekg(0, std::ios::beg);
-    data.resize(size);
-    ifs.read((char*)data.data(), size);
-    return true;
-}
-
-bool rpc_server::set_tensor_hash(const std::vector<uint8_t>& input, rpc_msg_set_tensor_hash_rsp& response)
-{
-    // serialization format: | rpc_tensor | offset (8 bytes) | hash (8 bytes) |
-    if (input.size() != sizeof(rpc_tensor) + 16) {
-        return false;
-    }
-    const rpc_tensor* in_tensor = (const rpc_tensor*)input.data();
+    const rpc_tensor * in_tensor = (const rpc_tensor *)input.data();
     uint64_t offset;
     memcpy(&offset, input.data() + sizeof(rpc_tensor), sizeof(offset));
-    const uint64_t* hash = (const uint64_t*)(input.data() + sizeof(rpc_tensor) + sizeof(offset));
-    std::vector<uint8_t> cached_file;
-    if (!get_cached_file(*hash, cached_file)) {
-        response.result = 0;
-        return true;
-    }
-    size_t size = cached_file.size();
+    uint64_t size;
+    memcpy(&size, input.data() + sizeof(rpc_tensor) + sizeof(offset), sizeof(size));
+
     struct ggml_init_params params {
         /*.mem_size   =*/ ggml_tensor_overhead(),
-            /*.mem_buffer =*/ NULL,
-            /*.no_alloc   =*/ true,
+        /*.mem_buffer =*/ NULL,
+        /*.no_alloc   =*/ true,
     };
-    struct ggml_context* ctx = ggml_init(params);
-    ggml_tensor* tensor = deserialize_tensor(ctx, in_tensor);
+    struct ggml_context * ctx = ggml_init(params);
+    ggml_tensor * tensor = deserialize_tensor(ctx, in_tensor);
     if (tensor == nullptr) {
-        GGML_ABORT("[%s] error deserializing tensor\n", __func__);
+        GGML_PRINT_DEBUG("[%s] error deserializing tensor\n", __func__);
         ggml_free(ctx);
         return false;
     }
-    GGML_PRINT_DEBUG("[%s] buffer: %p, data: %p, offset: %" PRIu64 ", size: %zu, hash: %" PRIx64 "\n", __func__, (void*)tensor->buffer, tensor->data, offset, size, *hash);
+    GGML_PRINT_DEBUG("[%s] buffer: %p, data: %p, offset: %" PRIu64 ", size: %" PRIu64 "\n", __func__, (void*)tensor->buffer, tensor->data, offset, size);
 
     // sanitize tensor->data
     {
-        const size_t p0 = (size_t)ggml_backend_buffer_get_base(tensor->buffer);
+        const size_t p0 = (size_t) ggml_backend_buffer_get_base(tensor->buffer);
         const size_t p1 = p0 + ggml_backend_buffer_get_size(tensor->buffer);
 
-        if (in_tensor->data + offset < p0 || in_tensor->data + offset >= p1 || size >(p1 - in_tensor->data - offset)) {
-            GGML_PRINT_DEBUG("[%s] tensor data region (data=0x%" PRIx64 ", offset=%" PRIu64 ", size=%zu, hash=0x%" PRIx64 ") out of buffer bounds [0x%zx, 0x%zx)\n",
-                           __func__, in_tensor->data, offset, size, *hash, p0, p1);
-            return false;
+        if (in_tensor->data + offset < p0 || in_tensor->data + offset >= p1 || size > (p1 - in_tensor->data - offset)) {
+            GGML_ABORT("[%s] tensor->data out of bounds\n", __func__);
         }
     }
-    ggml_backend_tensor_set(tensor, cached_file.data(), offset, size);
-    response.result = 1;
-    ggml_free(ctx);
-    return true;
-}
-
-bool rpc_server::init_tensor(const rpc_msg_init_tensor_req& request) {
-    struct ggml_init_params params {
-        /*.mem_size   =*/ ggml_tensor_overhead(),
-            /*.mem_buffer =*/ NULL,
-            /*.no_alloc   =*/ true,
-    };
-    struct ggml_context* ctx = ggml_init(params);
-    ggml_tensor* tensor = deserialize_tensor(ctx, &request.tensor);
-    if (tensor == nullptr) {
-        GGML_PRINT_DEBUG("Null tensor pointer passed to server init_tensor function.\n");
-        ggml_free(ctx);
-        return false;
-    }
-
-    // Call the backend's buffer_init_tensor function
-    ggml_backend_buffer_t buffer = tensor->buffer;
-    if (buffer && buffer->iface.init_tensor) {
-        buffer->iface.init_tensor(buffer, tensor);
-    }
-    else {
-        GGML_PRINT_DEBUG("Null buffer for tensor passed to init_tensor function\n");
-    }
-
-    if (tensor->extra != nullptr) {
-        // This pointer can either be passed around client/server, or probably better stored server-side and kept track of.
-        // Currently unimplemented.
-        GGML_PRINT_DEBUG("tensor->extra populated by the backend, this is currently unsupported.\n");
-        ggml_free(ctx);
-        return false;
-    }
 
+    // output serialization format: | data (size bytes) |
+    output.resize(size, 0);
+    ggml_backend_tensor_get(tensor, output.data(), offset, size);
     ggml_free(ctx);
     return true;
 }
 
-bool rpc_server::get_tensor(const rpc_msg_get_tensor_req& request, std::vector<uint8_t>& response) {
-    struct ggml_init_params params {
-        /*.mem_size   =*/ ggml_tensor_overhead(),
-            /*.mem_buffer =*/ NULL,
-            /*.no_alloc   =*/ true,
-    };
-    struct ggml_context* ctx = ggml_init(params);
-    ggml_tensor* tensor = deserialize_tensor(ctx, &request.tensor);
-    if (tensor == nullptr) {
-        GGML_ABORT("[%s] error deserializing tensor\n", __func__);
-        ggml_free(ctx);
+bool rpc_server::copy_tensor(const std::vector<uint8_t> & input, std::vector<uint8_t> & output) {
+    // serialization format: | rpc_tensor src | rpc_tensor dst |
+    if (input.size() != 2*sizeof(rpc_tensor)) {
         return false;
     }
-    GGML_PRINT_DEBUG("[%s] buffer: %p, data: %p, offset: %" PRIu64 ", size: %" PRIu64 "\n", __func__, (void*)tensor->buffer, tensor->data, request.offset, request.size);
+    const rpc_tensor * rpc_src = (const rpc_tensor *)input.data();
+    const rpc_tensor * rpc_dst = (const rpc_tensor *)(input.data() + sizeof(rpc_src));
 
-    // sanitize tensor->data
-    {
-        const size_t p0 = (size_t)ggml_backend_buffer_get_base(tensor->buffer);
-        const size_t p1 = p0 + ggml_backend_buffer_get_size(tensor->buffer);
-
-        if (request.tensor.data + request.offset < p0 ||
-            request.tensor.data + request.offset >= p1 ||
-            request.size > (p1 - request.tensor.data - request.offset)) {
-                GGML_PRINT_DEBUG("[%s] requested tensor region (data=0x%" PRIx64 ", offset=%" PRIu64 ", size=%" PRIu64 ") out of buffer bounds [0x%zx, 0x%zx)\n",
-                               __func__, request.tensor.data, request.offset, request.size, p0, p1);
-                return false;
-        }
-    }
-
-    response.resize(request.size, 0);
-    ggml_backend_tensor_get(tensor, response.data(), request.offset, request.size);
-    ggml_free(ctx);
-    return true;
-}
-bool rpc_server::copy_tensor(const rpc_msg_copy_tensor_req& request, rpc_msg_copy_tensor_rsp& response) {
     struct ggml_init_params params {
-        /*.mem_size   =*/ 2 * ggml_tensor_overhead(),
-            /*.mem_buffer =*/ NULL,
-            /*.no_alloc   =*/ true,
+        /*.mem_size   =*/ 2*ggml_tensor_overhead(),
+        /*.mem_buffer =*/ NULL,
+        /*.no_alloc   =*/ true,
     };
-    struct ggml_context* ctx = ggml_init(params);
-    ggml_tensor* src = deserialize_tensor(ctx, &request.src);
-    ggml_tensor* dst = deserialize_tensor(ctx, &request.dst);
+    struct ggml_context * ctx = ggml_init(params);
+    ggml_tensor * src = deserialize_tensor(ctx, rpc_src);
+    ggml_tensor * dst = deserialize_tensor(ctx, rpc_dst);
     if (src == nullptr || dst == nullptr) {
-        GGML_ABORT("[%s] error deserializing tensors\n", __func__);
-        ggml_free(ctx);
-        return false;
-    }
-
-    uint64_t src_size = (uint64_t)ggml_nbytes(src);
-    uint64_t dst_data = (uint64_t)dst->data;
-    uint64_t dst_base = (uint64_t)ggml_backend_buffer_get_base(dst->buffer);
-    uint64_t dst_buf_sz = (uint64_t)ggml_backend_buffer_get_size(dst->buffer);
-
-    if (dst_data + src_size > dst_base + dst_buf_sz) {
-        GGML_PRINT_DEBUG("[%s] out-of-bounds write in rpc_server::copy_tensor:\n"
-            "    write range : [0x%" PRIx64 ", 0x%" PRIx64 "]\n"
-            "    buffer base: [0x%" PRIx64 ", 0x%" PRIx64 "]\n",
-            __func__,
-            dst_data,
-            dst_data + src_size,
-            dst_base,
-            dst_base + dst_buf_sz);
+        GGML_PRINT_DEBUG("[%s] error deserializing tensors\n", __func__);
         ggml_free(ctx);
         return false;
     }
-
-    GGML_PRINT_DEBUG("[%s] src->buffer: %p, dst->buffer: %p\n",
-        __func__, (void*)src->buffer, (void*)dst->buffer);
-
-    response.result = ggml_backend_buffer_copy_tensor(src, dst);
+    GGML_PRINT_DEBUG("[%s] src->buffer: %p, dst->buffer: %p\n", __func__, (void*)src->buffer, (void*)dst->buffer);
+    bool result = ggml_backend_buffer_copy_tensor(src, dst);
+    // output serialization format: | result (1 byte) |
+    output.resize(1, 0);
+    output[0] = result;
     ggml_free(ctx);
     return true;
 }
 
-ggml_tensor* rpc_server::create_node(uint64_t id,
-    struct ggml_context* ctx,
-    const std::unordered_map<uint64_t, const rpc_tensor*>& tensor_ptrs,
-    std::unordered_map<uint64_t, struct ggml_tensor*>& tensor_map) {
+ggml_tensor * rpc_server::create_node(uint64_t id,
+                                      struct ggml_context * ctx,
+                                      const std::unordered_map<uint64_t, const rpc_tensor*> & tensor_ptrs,
+                                      std::unordered_map<uint64_t, struct ggml_tensor*> & tensor_map) {
+    if (id == 0) {
+        return nullptr;
+    }
     if (tensor_map.find(id) != tensor_map.end()) {
         return tensor_map[id];
     }
-    // Safely find the tensor pointer
-    auto it_ptr = tensor_ptrs.find(id);
-    if (it_ptr == tensor_ptrs.end()) {
-        return nullptr;
-    }
-    const rpc_tensor * tensor = it_ptr->second;
-
+    const rpc_tensor * tensor = tensor_ptrs.at(id);
     struct ggml_tensor * result = deserialize_tensor(ctx, tensor);
     if (result == nullptr) {
         return nullptr;
     }
     tensor_map[id] = result;
     for (int i = 0; i < GGML_MAX_SRC; i++) {
-        // Check if the source ID is 0 before calling create_node recursively
-        if (tensor->src[i] == 0) {
-            result->src[i] = nullptr;
-        } else {
-            result->src[i] = create_node(tensor->src[i], ctx, tensor_ptrs, tensor_map);
-            // If the recursive call failed for a non-zero ID, propagate the error
-            if (result->src[i] == nullptr) {
-                GGML_PRINT_DEBUG("[%s] failed to create source node %d (src_id=%" PRIu64 ") for node id %" PRIu64 "\n",
-                               __func__, i, tensor->src[i], id);
-                // Must return nullptr to signal failure up the call stack
-                return nullptr;
-            }
-        }
-    }
-
-    // Handle view_src similarly
-    if (tensor->view_src == 0) {
-        result->view_src = nullptr;
-    } else {
-        result->view_src = create_node(tensor->view_src, ctx, tensor_ptrs, tensor_map);
-        // If the recursive call failed for a non-zero ID, propagate the error
-        if (result->view_src == nullptr) {
-            GGML_PRINT_DEBUG("[%s] failed to create view_src node (view_src_id=%" PRIu64 ") for node id %" PRIu64 "\n",
-                           __func__, tensor->view_src, id);
-            // Must return nullptr to signal failure up the call stack
-            return nullptr;
-        }
+        result->src[i] = create_node(tensor->src[i], ctx, tensor_ptrs, tensor_map);
     }
+    result->view_src = create_node(tensor->view_src, ctx, tensor_ptrs, tensor_map);
     result->view_offs = tensor->view_offs;
     return result;
 }
 
-bool rpc_server::graph_compute(const std::vector<uint8_t>& input, rpc_msg_graph_compute_rsp& response) {
+bool rpc_server::graph_compute(const std::vector<uint8_t> & input, std::vector<uint8_t> & output) {
     // serialization format:
     // | n_nodes (4 bytes) | nodes (n_nodes * sizeof(uint64_t) | n_tensors (4 bytes) | tensors (n_tensors * sizeof(rpc_tensor)) |
     if (input.size() < sizeof(uint32_t)) {
@@ -1393,27 +1046,26 @@ bool rpc_server::graph_compute(const std::vector<uint8_t>& input, rpc_msg_graph_
     }
     uint32_t n_nodes;
     memcpy(&n_nodes, input.data(), sizeof(n_nodes));
-    if (input.size() < sizeof(uint32_t) + n_nodes * sizeof(uint64_t) + sizeof(uint32_t)) {
+    if (input.size() < sizeof(uint32_t) + n_nodes*sizeof(uint64_t) + sizeof(uint32_t)) {
         return false;
     }
-    const uint64_t* nodes = (const uint64_t*)(input.data() + sizeof(n_nodes));
+    const uint64_t * nodes = (const uint64_t *)(input.data() + sizeof(n_nodes));
     uint32_t n_tensors;
-    memcpy(&n_tensors, input.data() + sizeof(n_nodes) + n_nodes * sizeof(uint64_t), sizeof(n_tensors));
-    if (input.size() < sizeof(uint32_t) + n_nodes * sizeof(uint64_t) + sizeof(uint32_t) + n_tensors * sizeof(rpc_tensor)) {
+    memcpy(&n_tensors, input.data() + sizeof(n_nodes) + n_nodes*sizeof(uint64_t), sizeof(n_tensors));
+    if (input.size() < sizeof(uint32_t) + n_nodes*sizeof(uint64_t) + sizeof(uint32_t) + n_tensors*sizeof(rpc_tensor)) {
         return false;
     }
-    const rpc_tensor* tensors = (const rpc_tensor*)(input.data() + sizeof(n_nodes) + n_nodes * sizeof(uint64_t) + sizeof(n_tensors));
+    const rpc_tensor * tensors = (const rpc_tensor *)(input.data() + sizeof(n_nodes) + n_nodes*sizeof(uint64_t) + sizeof(n_tensors));
     GGML_PRINT_DEBUG("[%s] n_nodes: %u, n_tensors: %u\n", __func__, n_nodes, n_tensors);
 
-    size_t buf_size = ggml_tensor_overhead() * (n_nodes + n_tensors) + ggml_graph_overhead_custom(n_nodes, false);
-
+    static size_t buf_size = ggml_tensor_overhead()*(n_nodes + n_tensors) + ggml_graph_overhead_custom(n_nodes, false);
     struct ggml_init_params params = {
         /*.mem_size   =*/ buf_size,
         /*.mem_buffer =*/ NULL,
         /*.no_alloc   =*/ true,
     };
-    struct ggml_context* ctx = ggml_init(params);
-    struct ggml_cgraph* graph = ggml_new_graph_custom(ctx, n_nodes, false);
+    struct ggml_context * ctx = ggml_init(params);
+    struct ggml_cgraph * graph = ggml_new_graph_custom(ctx, n_nodes, false);
     graph->n_nodes = n_nodes;
     std::unordered_map<uint64_t, const rpc_tensor*> tensor_ptrs;
     for (uint32_t i = 0; i < n_tensors; i++) {
@@ -1424,17 +1076,11 @@ bool rpc_server::graph_compute(const std::vector<uint8_t>& input, rpc_msg_graph_
         int64_t id;
         memcpy(&id, &nodes[i], sizeof(id));
         graph->nodes[i] = create_node(id, ctx, tensor_ptrs, tensor_map);
-
-        // Check if create_node failed for a *non-zero* ID.
-        // If id was 0, create_node returning nullptr is expected.
-        // If id was non-zero and create_node returned nullptr, it indicates a deserialization error.
-        if (graph->nodes[i] == nullptr && id != 0) {
-            GGML_PRINT_DEBUG("[%s] failed to create graph node %d (id=%" PRId64 ")\n", __func__, i, id);
-            return false;
-        }
     }
     ggml_status status = ggml_backend_graph_compute(backend, graph);
-    response.result = status;
+    // output serialization format: | status (1 byte) |
+    output.resize(1, 0);
+    output[0] = status;
     ggml_free(ctx);
     return true;
 }
@@ -1444,229 +1090,92 @@ rpc_server::~rpc_server() {
         ggml_backend_buffer_free(buffer);
     }
 }
-static void rpc_serve_client(ggml_backend_t backend, const char* cache_dir,
-    sockfd_t sockfd, size_t free_mem, size_t total_mem) {
-    rpc_server server(backend, cache_dir);
-    uint8_t cmd;
-    if (!recv_data(sockfd, &cmd, 1)) {
-        return;
-    }
-    // the first command sent by the client must be HELLO
-    if (cmd != RPC_CMD_HELLO) {
-        fprintf(stderr, "Expected HELLO command, update client\n");
-        return;
-    }
-    if (!recv_msg(sockfd, nullptr, 0)) {
-        return;
-    }
-    rpc_msg_hello_rsp response;
-    server.hello(response);
-    if (!send_msg(sockfd, &response, sizeof(response))) {
-        return;
-    }
+
+static void rpc_serve_client(ggml_backend_t backend, sockfd_t sockfd, size_t free_mem, size_t total_mem) {
+    rpc_server server(backend);
     while (true) {
+        uint8_t cmd;
         if (!recv_data(sockfd, &cmd, 1)) {
             break;
         }
-        if (cmd >= RPC_CMD_COUNT) {
-            // fail fast if the command is invalid
-            fprintf(stderr, "Unknown command: %d\n", cmd);
-            break;
-        }
-        switch (cmd) {
-        case RPC_CMD_HELLO: {
-            // HELLO command is handled above
-            return;
-        }
-        case RPC_CMD_ALLOC_BUFFER: {
-            rpc_msg_alloc_buffer_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
-            }
-            rpc_msg_alloc_buffer_rsp response;
-            server.alloc_buffer(request, response);
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
-            break;
-        }
-        case RPC_CMD_GET_ALLOC_SIZE: {
-            rpc_msg_get_alloc_size_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
-            }
-            rpc_msg_get_alloc_size_rsp response;
-            server.get_alloc_size(request, response);
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
+        std::vector<uint8_t> input;
+        std::vector<uint8_t> output;
+        uint64_t input_size;
+        if (!recv_data(sockfd, &input_size, sizeof(input_size))) {
             break;
         }
-        case RPC_CMD_GET_ALIGNMENT: {
-            if (!recv_msg(sockfd, nullptr, 0)) {
-                return;
-            }
-            rpc_msg_get_alignment_rsp response;
-            server.get_alignment(response);
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
+        input.resize(input_size);
+        if (!recv_data(sockfd, input.data(), input_size)) {
             break;
         }
-        case RPC_CMD_GET_MAX_SIZE: {
-            if (!recv_msg(sockfd, nullptr, 0)) {
-                return;
-            }
-            rpc_msg_get_max_size_rsp response;
-            server.get_max_size(response);
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
-            break;
-        }
-        case RPC_CMD_BUFFER_GET_BASE: {
-            rpc_msg_buffer_get_base_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
-            }
-            rpc_msg_buffer_get_base_rsp response;
-            if (!server.buffer_get_base(request, response)) {
-                return;
-            }
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
-            break;
-        }
-        case RPC_CMD_FREE_BUFFER: {
-            rpc_msg_free_buffer_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
-            }
-            if (!server.free_buffer(request)) {
-                return;
-            }
-            if (!send_msg(sockfd, nullptr, 0)) {
-                return;
-            }
-            break;
-        }
-        case RPC_CMD_BUFFER_CLEAR: {
-            rpc_msg_buffer_clear_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
-            }
-            if (!server.buffer_clear(request)) {
-                return;
-            }
-            if (!send_msg(sockfd, nullptr, 0)) {
-                return;
+        bool ok = true;
+        switch (cmd) {
+            case ALLOC_BUFFER: {
+                ok = server.alloc_buffer(input, output);
+                break;
             }
-            break;
-        }
-        case RPC_CMD_SET_TENSOR: {
-            std::vector<uint8_t> input;
-            if (!recv_msg(sockfd, input)) {
-                return;
+            case GET_ALIGNMENT: {
+                server.get_alignment(output);
+                break;
             }
-            if (!server.set_tensor(input)) {
-                return;
+            case GET_MAX_SIZE: {
+                server.get_max_size(output);
+                break;
             }
-            break;
-        }
-        case RPC_CMD_SET_TENSOR_HASH: {
-            std::vector<uint8_t> input;
-            if (!recv_msg(sockfd, input)) {
-                return;
+            case BUFFER_GET_BASE: {
+                ok = server.buffer_get_base(input, output);
+                break;
             }
-            rpc_msg_set_tensor_hash_rsp response;
-            if (!server.set_tensor_hash(input, response)) {
-                return;
+            case FREE_BUFFER: {
+                ok = server.free_buffer(input);
+                break;
             }
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
+            case BUFFER_CLEAR: {
+                ok = server.buffer_clear(input);
+                break;
             }
-            break;
-        }
-        case RPC_CMD_INIT_TENSOR: {
-            rpc_msg_init_tensor_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
+            case SET_TENSOR: {
+                ok = server.set_tensor(input);
+                break;
             }
-            if (!server.init_tensor(request)) {
-                return;
+            case GET_TENSOR: {
+                ok = server.get_tensor(input, output);
+                break;
             }
-            if (!send_msg(sockfd, nullptr, 0)) {
-                return;
+            case COPY_TENSOR: {
+                ok = server.copy_tensor(input, output);
+                break;
             }
-            break;
-        }
-        case RPC_CMD_GET_TENSOR: {
-            rpc_msg_get_tensor_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
+            case GRAPH_COMPUTE: {
+                ok = server.graph_compute(input, output);
+                break;
             }
-            std::vector<uint8_t> response;
-            if (!server.get_tensor(request, response)) {
-                return;
+            case GET_DEVICE_MEMORY: {
+                // output serialization format: | free (8 bytes) | total (8 bytes) |
+                output.resize(2*sizeof(uint64_t), 0);
+                memcpy(output.data(), &free_mem, sizeof(free_mem));
+                memcpy(output.data() + sizeof(uint64_t), &total_mem, sizeof(total_mem));
+                break;
             }
-            if (!send_msg(sockfd, response.data(), response.size())) {
-                return;
+            default: {
+                fprintf(stderr, "Unknown command: %d\n", cmd);
+                ok = false;
             }
-            break;
         }
-        case RPC_CMD_COPY_TENSOR: {
-            rpc_msg_copy_tensor_req request;
-            if (!recv_msg(sockfd, &request, sizeof(request))) {
-                return;
-            }
-            rpc_msg_copy_tensor_rsp response;
-            if (!server.copy_tensor(request, response)) {
-                return;
-            }
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
+        if (!ok) {
             break;
         }
-        case RPC_CMD_GRAPH_COMPUTE: {
-            std::vector<uint8_t> input;
-            if (!recv_msg(sockfd, input)) {
-                return;
-            }
-            rpc_msg_graph_compute_rsp response;
-            if (!server.graph_compute(input, response)) {
-                return;
-            }
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
+        uint64_t output_size = output.size();
+        if (!send_data(sockfd, &output_size, sizeof(output_size))) {
             break;
         }
-        case RPC_CMD_GET_DEVICE_MEMORY: {
-            if (!recv_msg(sockfd, nullptr, 0)) {
-                return;
-            }
-            rpc_msg_get_device_memory_rsp response;
-            response.free_mem = free_mem;
-            response.total_mem = total_mem;
-            if (!send_msg(sockfd, &response, sizeof(response))) {
-                return;
-            }
+        if (!send_data(sockfd, output.data(), output_size)) {
             break;
         }
-        default: {
-            fprintf(stderr, "Unknown command: %d\n", cmd);
-            return;
-        }
-        }
     }
 }
 
-
-void ggml_backend_rpc_start_server(ggml_backend_t backend, const char* endpoint,
-    const char* cache_dir,
-    size_t free_mem, size_t total_mem) {
+void start_rpc_server(ggml_backend_t backend, const char * endpoint, size_t free_mem, size_t total_mem) {
     std::string host;
     int port;
     if (!parse_endpoint(endpoint, host, port)) {
@@ -1694,10 +1203,8 @@ void ggml_backend_rpc_start_server(ggml_backend_t backend, const char* endpoint,
             return;
         }
         printf("Accepted client connection, free_mem=%zu, total_mem=%zu\n", free_mem, total_mem);
-        fflush(stdout);
-        rpc_serve_client(backend, cache_dir, client_socket->fd, free_mem, total_mem);
+        rpc_serve_client(backend, client_socket->fd, free_mem, total_mem);
         printf("Client connection closed\n");
-        fflush(stdout);
     }
 #ifdef _WIN32
     WSACleanup();
diff --git a/ggml/src/ggml.c b/ggml/src/ggml.c
index 3ff294cc..5bb75d32 100644
--- a/ggml/src/ggml.c
+++ b/ggml/src/ggml.c
@@ -4935,7 +4935,7 @@ static struct ggml_object * ggml_new_object(struct ggml_context * ctx, enum ggml
 
     if (cur_end + size_needed + GGML_OBJECT_SIZE > ctx->mem_size) {
         GGML_PRINT("%s: not enough space in the context's memory pool (needed %zu, available %zu)\n",
-            __func__, cur_end + size_needed + GGML_OBJECT_SIZE, ctx->mem_size);
+                __func__, cur_end + size_needed, ctx->mem_size);
         assert(false);
         return NULL;
     }
diff --git a/src/unicode.cpp b/src/unicode.cpp
index a57456ea..cfffde0d 100644
--- a/src/unicode.cpp
+++ b/src/unicode.cpp
@@ -18,7 +18,6 @@
 #include <vector>
 #include <locale>
 #include <codecvt>
-#include <iostream>
 
 size_t unicode_len_utf8(char src) {
     const size_t lookup[] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 3, 4 };
@@ -26,7 +25,7 @@ size_t unicode_len_utf8(char src) {
     return lookup[highbits];
 }
 
-static std::string unicode_cpts_to_utf8(const std::vector<uint32_t>& cps) {
+static std::string unicode_cpts_to_utf8(const std::vector<uint32_t> & cps) {
     std::string result;
     for (size_t i = 0; i < cps.size(); ++i) {
         result.append(unicode_cpt_to_utf8(cps[i]));
@@ -34,7 +33,7 @@ static std::string unicode_cpts_to_utf8(const std::vector<uint32_t>& cps) {
     return result;
 }
 
-uint32_t unicode_cpt_from_utf8(const std::string& utf8, size_t& offset) {
+uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) {
     assert(offset < utf8.size());
     if (!(utf8[offset + 0] & 0x80)) {
         auto result = utf8[offset + 0];
@@ -45,7 +44,7 @@ uint32_t unicode_cpt_from_utf8(const std::string& utf8, size_t& offset) {
         throw std::invalid_argument("invalid character");
     }
     if (!(utf8[offset + 0] & 0x20)) {
-        if (offset + 1 >= utf8.size() || !((utf8[offset + 1] & 0xc0) == 0x80)) {
+        if (offset + 1 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80)) {
             throw std::invalid_argument("invalid character");
         }
         auto result = ((utf8[offset + 0] & 0x1f) << 6) | (utf8[offset + 1] & 0x3f);
@@ -53,7 +52,7 @@ uint32_t unicode_cpt_from_utf8(const std::string& utf8, size_t& offset) {
         return result;
     }
     if (!(utf8[offset + 0] & 0x10)) {
-        if (offset + 2 >= utf8.size() || !((utf8[offset + 1] & 0xc0) == 0x80) || !((utf8[offset + 2] & 0xc0) == 0x80)) {
+        if (offset + 2 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80)) {
             throw std::invalid_argument("invalid character");
         }
         auto result = ((utf8[offset + 0] & 0x0f) << 12) | ((utf8[offset + 1] & 0x3f) << 6) | (utf8[offset + 2] & 0x3f);
@@ -61,7 +60,7 @@ uint32_t unicode_cpt_from_utf8(const std::string& utf8, size_t& offset) {
         return result;
     }
     if (!(utf8[offset + 0] & 0x08)) {
-        if (offset + 3 >= utf8.size() || !((utf8[offset + 1] & 0xc0) == 0x80) || !((utf8[offset + 2] & 0xc0) == 0x80) || !((utf8[offset + 3] & 0xc0) == 0x80)) {
+        if (offset + 3 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80) || !((utf8[offset + 3] & 0xc0) == 0x80)) {
             throw std::invalid_argument("invalid character");
         }
         auto result = ((utf8[offset + 0] & 0x07) << 18) | ((utf8[offset + 1] & 0x3f) << 12) | ((utf8[offset + 2] & 0x3f) << 6) | (utf8[offset + 3] & 0x3f);
@@ -123,10 +122,10 @@ uint32_t unicode_cpt_from_utf8(const std::string& utf8, size_t& offset) {
 static std::vector<codepoint_flags> unicode_cpt_flags_array() {
     std::vector<codepoint_flags> cpt_flags(MAX_CODEPOINTS, codepoint_flags::UNDEFINED);
 
-    assert(unicode_ranges_flags.front().first == 0);
-    assert(unicode_ranges_flags.back().first == MAX_CODEPOINTS);
+    assert (unicode_ranges_flags.front().first == 0);
+    assert (unicode_ranges_flags.back().first == MAX_CODEPOINTS);
     for (size_t i = 1; i < unicode_ranges_flags.size(); ++i) {
-        const auto range_ini = unicode_ranges_flags[i - 1];  // codepoint_ini, flags
+        const auto range_ini = unicode_ranges_flags[i-1];  // codepoint_ini, flags
         const auto range_end = unicode_ranges_flags[i];    // codepoint_end, flags
         for (uint32_t cpt = range_ini.first; cpt < range_end.first; ++cpt) {
             cpt_flags[cpt] = range_ini.second;
@@ -145,7 +144,7 @@ static std::vector<codepoint_flags> unicode_cpt_flags_array() {
         cpt_flags[p.second].is_uppercase = true;
     }
 
-    for (auto& range : unicode_ranges_nfd) {  // start, last, nfd
+    for (auto &range : unicode_ranges_nfd) {  // start, last, nfd
         cpt_flags[range.nfd].is_nfd = true;
     }
 
@@ -200,55 +199,22 @@ static std::unordered_map<std::string, uint8_t> unicode_utf8_to_byte_map() {
     return map;
 }
 
-static inline bool  is_valid_utf8(const std::string& str) {
-    int remaining_bytes = 0; // 当前多字节字符剩余的字节数
-    for (unsigned char c : str) {
-        if (remaining_bytes == 0) {
-            if ((c & 0x80) == 0x00) continue;          // 1字节字符
-            else if ((c & 0xE0) == 0xC0) remaining_bytes = 1; // 2字节
-            else if ((c & 0xF0) == 0xE0) remaining_bytes = 2; // 3字节
-            else if ((c & 0xF8) == 0xF0) remaining_bytes = 3; // 4字节
-            else return false; // 非法起始字节
-        }
-        else {
-            // 检查后续字节是否为10xxxxxx
-            if ((c & 0xC0) != 0x80)
-            {
-                return false;
-            }
-            remaining_bytes--;
-        }
-    }
-    return (remaining_bytes == 0); // 确保多字节字符完整
-}
-
-static inline std::wstring unicode_wstring_from_utf8(const std::string& s) {
-#if defined(__clang__)
-    // disable C++17 deprecation warning for std::codecvt_utf8
-#    pragma clang diagnostic push
-#    pragma clang diagnostic ignored "-Wdeprecated-declarations"
-#endif
-    bool isvalid = is_valid_utf8(s);
+static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
     std::wstring_convert<std::codecvt_utf8<wchar_t>> conv;
-
-#if defined(__clang__)
-#    pragma clang diagnostic pop
-#endif
-
     return conv.from_bytes(s);
 }
 
-static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string>& bpe_words) {
+static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string> & bpe_words) {
     std::vector<std::string> bpe_encoded_words;
-    for (const auto& word : bpe_words) {
+    for (const auto & word : bpe_words) {
         std::string text_utf;
-        auto utf_word = unicode_cpts_from_utf8(word);
+        auto utf_word =  unicode_cpts_from_utf8(word);
         for (size_t i = 0; i < utf_word.size(); ++i) {
             text_utf += unicode_cpt_to_utf8(utf_word[i]);
         }
 
         std::string encoded_token;
-        for (char& c : text_utf) {
+        for (char & c : text_utf) {
             encoded_token += unicode_byte_to_utf8(c);
         }
         bpe_encoded_words.emplace_back(encoded_token);
@@ -257,7 +223,7 @@ static std::vector<std::string> unicode_byte_encoding_process(const std::vector<
 }
 
 // GPT2 system regex:  's|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+
-static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string& text, const std::vector<size_t>& offsets) {
+static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & text, const std::vector<size_t> & offsets) {
     std::vector<size_t> bpe_offsets; // store the offset of each word
     bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
 
@@ -271,16 +237,16 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string& te
         start = offset_end;
 
         static const uint32_t OUT_OF_RANGE = 0xFFFFFFFF;
-        auto _get_cpt = [&](const size_t pos) -> uint32_t {
+        auto _get_cpt = [&] (const size_t pos) -> uint32_t {
             return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
         };
 
-        auto _get_flags = [&](const size_t pos) -> codepoint_flags {
+        auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
             return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
         };
 
         size_t _prev_end = offset_ini;
-        auto _add_token = [&](const size_t end) -> size_t {
+        auto _add_token = [&] (const size_t end) -> size_t {
             assert(_prev_end <= end && end <= offset_end);
             size_t len = end - _prev_end;
             if (len > 0) {
@@ -296,29 +262,29 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string& te
             return len;
         };
 
-        for (size_t pos = offset_ini; pos < offset_end; /*pos++*/) {
+        for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
             const uint32_t cpt = _get_cpt(pos);
             const auto flags = _get_flags(pos);
 
             // regex: 's|'t|'re|'ve|'m|'ll|'d
-            if (cpt == '\'' && pos + 1 < offset_end) {
-                uint32_t cpt_next = _get_cpt(pos + 1);
+            if (cpt == '\'' && pos+1 < offset_end) {
+                uint32_t cpt_next = _get_cpt(pos+1);
                 if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
-                    pos += _add_token(pos + 2);
+                    pos += _add_token(pos+2);
                     continue;
                 }
-                if (pos + 2 < offset_end) {
-                    uint32_t cpt_next_next = _get_cpt(pos + 2);
+                if (pos+2 < offset_end) {
+                    uint32_t cpt_next_next = _get_cpt(pos+2);
                     if ((cpt_next == 'r' && cpt_next_next == 'e') ||
                         (cpt_next == 'v' && cpt_next_next == 'e') ||
                         (cpt_next == 'l' && cpt_next_next == 'l')) {
-                        pos += _add_token(pos + 3);
+                        pos += _add_token(pos+3);
                         continue;
                     }
                 }
             }
 
-            auto flags2 = (cpt == ' ' ? _get_flags(pos + 1) : flags);
+            auto flags2 = (cpt == ' ' ? _get_flags(pos+1) : flags);
             // regex: <space>?\p{L}+
             if (flags2.is_letter) {
                 pos += (cpt == ' ');
@@ -348,12 +314,12 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string& te
             }
 
             size_t num_whitespaces = 0;
-            while (_get_flags(pos + num_whitespaces).is_whitespace) {
+            while (_get_flags(pos+num_whitespaces).is_whitespace) {
                 num_whitespaces++;
             }
 
             // regex: \s+(?!\S)
-            if (num_whitespaces > 1 && _get_cpt(pos + num_whitespaces) != OUT_OF_RANGE) {
+            if (num_whitespaces > 1 && _get_cpt(pos+num_whitespaces) != OUT_OF_RANGE) {
                 pos += num_whitespaces - 1;
                 _add_token(pos);
                 continue;
@@ -375,7 +341,7 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string& te
 }
 
 // LLAMA3 system regex: "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"
-static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string& text, const std::vector<size_t>& offsets) {
+static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string & text, const std::vector<size_t> & offsets) {
     std::vector<size_t> bpe_offsets; // store the offset of each word
     bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
 
@@ -389,16 +355,16 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
         start = offset_end;
 
         static const uint32_t OUT_OF_RANGE = 0xFFFFFFFF;
-        auto _get_cpt = [&](const size_t pos) -> uint32_t {
+        auto _get_cpt = [&] (const size_t pos) -> uint32_t {
             return (offset_ini <= pos && pos < offset_end) ? cpts[pos] : OUT_OF_RANGE;
         };
 
-        auto _get_flags = [&](const size_t pos) -> codepoint_flags {
+        auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
             return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
         };
 
         size_t _prev_end = offset_ini;
-        auto _add_token = [&](const size_t end) -> size_t {
+        auto _add_token = [&] (const size_t end) -> size_t {
             assert(_prev_end <= end && end <= offset_end);
             size_t len = end - _prev_end;
             if (len > 0) {
@@ -414,23 +380,23 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
             return len;
         };
 
-        for (size_t pos = offset_ini; pos < offset_end; /*pos++*/) {
+        for (size_t pos = offset_ini; pos < offset_end; /*pos++*/ ) {
             const uint32_t cpt = _get_cpt(pos);
             const auto flags = _get_flags(pos);
 
             // regex: (?i:'s|'t|'re|'ve|'m|'ll|'d) // case insensitive
-            if (cpt == '\'' && pos + 1 < offset_end) {
-                uint32_t cpt_next = unicode_tolower(_get_cpt(pos + 1));
+            if (cpt == '\'' && pos+1 < offset_end) {
+                uint32_t cpt_next = unicode_tolower(_get_cpt(pos+1));
                 if (cpt_next == 's' || cpt_next == 't' || cpt_next == 'm' || cpt_next == 'd') {
-                    pos += _add_token(pos + 2);
+                    pos += _add_token(pos+2);
                     continue;
                 }
-                if (pos + 2 < offset_end) {
-                    uint32_t cpt_next_next = unicode_tolower(_get_cpt(pos + 2));
+                if (pos+2 < offset_end) {
+                    uint32_t cpt_next_next = unicode_tolower(_get_cpt(pos+2));
                     if ((cpt_next == 'r' && cpt_next_next == 'e') ||
                         (cpt_next == 'v' && cpt_next_next == 'e') ||
                         (cpt_next == 'l' && cpt_next_next == 'l')) {
-                        pos += _add_token(pos + 3);
+                        pos += _add_token(pos+3);
                         continue;
                     }
                 }
@@ -438,7 +404,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
 
             // regex: [^\r\n\p{L}\p{N}]?\p{L}+
             if (!(cpt == '\r' || cpt == '\n' || flags.is_number)) {
-                if (flags.is_letter || _get_flags(pos + 1).is_letter) {  // one or more letters
+                if (flags.is_letter || _get_flags(pos+1).is_letter) {  // one or more letters
                     pos++;
                     while (_get_flags(pos).is_letter) {
                         pos++;
@@ -452,7 +418,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
             if (flags.is_number) {
                 size_t ini = pos;
                 while (_get_flags(pos).is_number) {
-                    if (++pos - ini >= 3) {
+                    if (++pos - ini >= 3 ) {
                         _add_token(pos);
                         ini = pos;
                     }
@@ -462,7 +428,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
             }
 
             // regex: <space>?[^\s\p{L}\p{N}]+[\r\n]*
-            auto flags2 = (cpt == ' ' ? _get_flags(pos + 1) : flags);
+            auto flags2 = (cpt == ' ' ? _get_flags(pos+1) : flags);
             if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags.as_uint()) {
                 pos += (cpt == ' ');
                 while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
@@ -478,8 +444,8 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
 
             size_t num_whitespaces = 0;
             size_t last_end_r_or_n = 0;
-            while (_get_flags(pos + num_whitespaces).is_whitespace) {
-                uint32_t cpt2 = _get_cpt(pos + num_whitespaces);
+            while (_get_flags(pos+num_whitespaces).is_whitespace) {
+                uint32_t cpt2 = _get_cpt(pos+num_whitespaces);
                 if (cpt2 == '\r' || cpt2 == '\n') {
                     last_end_r_or_n = pos + num_whitespaces + 1;
                 }
@@ -494,7 +460,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
             }
 
             // regex: \s+(?!\S)
-            if (num_whitespaces > 1 && _get_cpt(pos + num_whitespaces) != OUT_OF_RANGE) {
+            if (num_whitespaces > 1 && _get_cpt(pos+num_whitespaces) != OUT_OF_RANGE) {
                 pos += num_whitespaces - 1;
                 _add_token(pos);
                 continue;
@@ -516,7 +482,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string&
 }
 
 // use std::wregex to split the text
-static std::vector<size_t> unicode_regex_split_stl(const std::wstring& wtext, const std::wstring& regex_expr, const std::vector<size_t>& offsets) {
+static std::vector<size_t> unicode_regex_split_stl(const std::wstring & wtext, const std::wstring & regex_expr, const std::vector<size_t> & offsets) {
     std::wregex expr(regex_expr);
     std::vector<size_t> bpe_offsets; // store the offset of each word
     bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
@@ -536,7 +502,7 @@ static std::vector<size_t> unicode_regex_split_stl(const std::wstring& wtext, co
             ++it;
         }
 
-        if (start_idx < (int64_t)offset) {
+        if (start_idx < (int64_t) offset) {
             bpe_offsets.emplace_back(offset - start_idx);
         }
         start += offset;
@@ -546,7 +512,7 @@ static std::vector<size_t> unicode_regex_split_stl(const std::wstring& wtext, co
 }
 
 // use std::regex to split the text
-static std::vector<size_t> unicode_regex_split_stl(const std::string& text, const std::string& regex_expr, const std::vector<size_t>& offsets) {
+static std::vector<size_t> unicode_regex_split_stl(const std::string & text, const std::string & regex_expr, const std::vector<size_t> & offsets) {
     std::regex expr(regex_expr);
     std::vector<size_t> bpe_offsets; // store the offset of each word
     bpe_offsets.reserve(offsets.size()); // Reserve memory for the approximate size
@@ -566,7 +532,7 @@ static std::vector<size_t> unicode_regex_split_stl(const std::string& text, cons
             ++it;
         }
 
-        if (start_idx < (int64_t)offset) {
+        if (start_idx < (int64_t) offset) {
             bpe_offsets.emplace_back(offset - start_idx);
         }
         start += offset;
@@ -575,15 +541,14 @@ static std::vector<size_t> unicode_regex_split_stl(const std::string& text, cons
     return bpe_offsets;
 }
 
-static std::vector<size_t> unicode_regex_split_custom(const std::string& text, const std::string& regex_expr, const std::vector<size_t>& offsets) {
+static std::vector<size_t> unicode_regex_split_custom(const std::string & text, const std::string & regex_expr, const std::vector<size_t> & offsets) {
     std::vector<size_t> bpe_offsets;
 
     if (regex_expr == "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)") {
         bpe_offsets = unicode_regex_split_custom_gpt2(text, offsets);
-    }
-    else if (
-        regex_expr == "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" ||
-        regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
+    } else if (
+            regex_expr == "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" ||
+            regex_expr == "(?:'[sS]|'[tT]|'[rR][eE]|'[vV][eE]|'[mM]|'[lL][lL]|'[dD])|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+") {
 
         bpe_offsets = unicode_regex_split_custom_llama3(text, offsets);
     }
@@ -624,8 +589,8 @@ std::string unicode_cpt_to_utf8(uint32_t cp) {
     throw std::invalid_argument("invalid codepoint");
 }
 
-std::vector<uint32_t> unicode_cpts_normalize_nfd(const std::vector<uint32_t>& cpts) {
-    auto comp = [](const uint32_t cpt, const range_nfd& range) {
+std::vector<uint32_t> unicode_cpts_normalize_nfd(const std::vector<uint32_t> & cpts) {
+    auto comp = [] (const uint32_t cpt, const range_nfd & range) {
         return cpt < range.first;
     };
     std::vector<uint32_t> result(cpts.size());
@@ -637,7 +602,7 @@ std::vector<uint32_t> unicode_cpts_normalize_nfd(const std::vector<uint32_t>& cp
     return result;
 }
 
-std::vector<uint32_t> unicode_cpts_from_utf8(const std::string& utf8) {
+std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8) {
     std::vector<uint32_t> result;
     result.reserve(utf8.size());
     size_t offset = 0;
@@ -653,7 +618,7 @@ codepoint_flags unicode_cpt_flags(const uint32_t cp) {
     return cp < cpt_flags.size() ? cpt_flags[cp] : undef;
 }
 
-codepoint_flags unicode_cpt_flags(const std::string& utf8) {
+codepoint_flags unicode_cpt_flags(const std::string & utf8) {
     static const codepoint_flags undef(codepoint_flags::UNDEFINED);
     if (utf8.empty()) {
         return undef;  // undefined
@@ -667,7 +632,7 @@ std::string unicode_byte_to_utf8(uint8_t byte) {
     return map.at(byte);
 }
 
-uint8_t unicode_utf8_to_byte(const std::string& utf8) {
+uint8_t unicode_utf8_to_byte(const std::string & utf8) {
     static std::unordered_map<std::string, uint8_t> map = unicode_utf8_to_byte_map();
     return map.at(utf8);
 }
@@ -677,7 +642,7 @@ uint32_t unicode_tolower(uint32_t cp) {
     return it == unicode_map_lowercase.end() ? cp : it->second;
 }
 
-std::vector<std::string> unicode_regex_split(const std::string& text, const std::vector<std::string>& regex_exprs) {
+std::vector<std::string> unicode_regex_split(const std::string & text, const std::vector<std::string> & regex_exprs) {
     // unicode categories
     static const std::map<std::string, int> k_ucat_enum = {
         { "\\p{N}", codepoint_flags::NUMBER },
@@ -706,9 +671,9 @@ std::vector<std::string> unicode_regex_split(const std::string& text, const std:
 
     // compute collapsed codepoints only if needed by at least one regex
     bool need_collapse = false;
-    for (auto& regex_expr : regex_exprs) {
+    for (auto & regex_expr : regex_exprs) {
         // search for unicode categories
-        for (const auto& ucat : k_ucat_enum) {
+        for (const auto & ucat : k_ucat_enum) {
             if (std::string::npos != regex_expr.find(ucat.first)) {
                 need_collapse = true;
                 break;
@@ -737,20 +702,18 @@ std::vector<std::string> unicode_regex_split(const std::string& text, const std:
             if (flags.is_whitespace) {
                 //NOTE: C++ std::regex \s does not mach 0x85, Rust and Python regex does.
                 //text_collapsed[i] = (char) 0x85;  // <Next Line> as whitespace fallback
-                text_collapsed[i] = (char)0x0B;    // <vertical tab> as whitespace fallback
-            }
-            else if (k_ucat_cpt.find(flags.category_flag()) != k_ucat_cpt.end()) {
+                text_collapsed[i] = (char) 0x0B;    // <vertical tab> as whitespace fallback
+            } else if (k_ucat_cpt.find(flags.category_flag()) != k_ucat_cpt.end()) {
                 text_collapsed[i] = k_ucat_cpt.at(flags.category_flag());
-            }
-            else {
-                text_collapsed[i] = (char)0xD0; // fallback
+            } else {
+                text_collapsed[i] = (char) 0xD0; // fallback
             }
         }
     }
 
     std::vector<size_t> bpe_offsets = { cpts.size() };
 
-    for (auto& regex_expr : regex_exprs) {
+    for (auto & regex_expr : regex_exprs) {
         // first, see if we have an efficient custom regex implementation
         auto tmp = unicode_regex_split_custom(text, regex_expr, bpe_offsets);
 
@@ -764,7 +727,7 @@ std::vector<std::string> unicode_regex_split(const std::string& text, const std:
             // if a unicode category is used in the regex, we use the collapsed text and replace the unicode category
             // with the corresponding collapsed representation
             bool use_collapsed = false;
-            for (auto& ucat : k_ucat_enum) {
+            for (auto & ucat : k_ucat_enum) {
                 if (std::string::npos != regex_expr.find(ucat.first)) {
                     use_collapsed = true;
                     break;
@@ -823,8 +786,7 @@ std::vector<std::string> unicode_regex_split(const std::string& text, const std:
                 //printf("text_collapsed: %s\n", text_collapsed.c_str());
                 //printf("regex_expr_collapsed: %s\n", regex_expr_collapsed.c_str());
                 bpe_offsets = unicode_regex_split_stl(text_collapsed, regex_expr_collapsed, bpe_offsets);
-            }
-            else {
+            } else {
                 // no unicode category used, we can use std::wregex directly
                 const std::wstring wregex_expr = unicode_wstring_from_utf8(regex_expr);
 
@@ -840,8 +802,7 @@ std::vector<std::string> unicode_regex_split(const std::string& text, const std:
                 //printf("regex_expr: %s\n", regex_expr.c_str());
                 bpe_offsets = unicode_regex_split_stl(wtext, wregex_expr, bpe_offsets);
             }
-        }
-        catch (std::regex_error& e) {
+        } catch (std::regex_error & e) {
             fprintf(stderr, "Failed to process regex: '%s'\n", regex_expr.c_str());
             fprintf(stderr, "Regex error: %s\n", e.what());
             throw std::runtime_error("Failed to process regex");
@@ -852,7 +813,7 @@ std::vector<std::string> unicode_regex_split(const std::string& text, const std:
     bpe_words.reserve(bpe_offsets.size()); // reserve memory for the approximate size
 
     size_t start = 0;
-    for (size_t& offset : bpe_offsets) {
+    for (size_t & offset : bpe_offsets) {
         bpe_words.emplace_back();
         for (size_t i = start; i < start + offset; ++i) {
             bpe_words.back() += unicode_cpt_to_utf8(cpts[i]);