Merge branch 'master' into ik/restore_k-quants_for_MoE

.github/workflows/nix-flake-update.yml

@@ -19,4 +19,4 @@ jobs:
           pr-labels: |
             nix
           pr-reviewers: philiptaron,SomeoneSerge
-          token: ${{ secrets.GITHUB_TOKEN }}
+          token: ${{ secrets.FLAKE_TOKEN }}

Package.swift

@@ -14,7 +14,7 @@ let package = Package(
         .library(name: "llama", targets: ["llama"]),
     ],
     dependencies: [
-        .package(url: "https://github.com/ggerganov/ggml.git", .branch("master"))
+        .package(url: "https://github.com/ggerganov/ggml.git", .revision("979cc23b345006504cfc1f67c0fdf627805e3319"))
     ],
     targets: [
         .target(

common/common.cpp

@@ -630,6 +630,12 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
                 break;
             }
             params.ppl_stride = std::stoi(argv[i]);
+        } else if (arg == "-stc" || arg == "--show_token_count") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            params.token_interval = std::stoi(argv[i]);
         } else if (arg == "--ppl-output-type") {
             if (++i >= argc) {
                 invalid_param = true;
@@ -944,6 +950,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("  --override-kv KEY=TYPE:VALUE\n");
     printf("                        advanced option to override model metadata by key. may be specified multiple times.\n");
     printf("                        types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
+    printf("  -stc N --show_token_count N\n");
+    printf("                        show consumed tokens every N tokens\n");
     printf("\n");
 #ifndef LOG_DISABLE_LOGS
     log_print_usage();

common/common.h

@@ -64,6 +64,7 @@ struct gpt_params {
     int32_t n_beams                         = 0;     // if non-zero then use beam search of given width.
     int32_t grp_attn_n                      = 1;     // group-attention factor
     int32_t grp_attn_w                      = 512;   // group-attention width
+    int32_t token_interval                  = 512;   // show token count every 512 tokens
     float   rope_freq_base                  = 0.0f;  // RoPE base frequency
     float   rope_freq_scale                 = 0.0f;  // RoPE frequency scaling factor
     float   yarn_ext_factor                 = -1.0f; // YaRN extrapolation mix factor
@@ -242,4 +243,3 @@ void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80);
 
 // Dump the KV cache view showing individual sequences in each cell (long output).
 void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);
-

examples/main/main.cpp

@@ -500,7 +500,7 @@ int main(int argc, char ** argv) {
     while ((n_remain != 0 && !is_antiprompt) || params.interactive) {
         // predict
         if (!embd.empty()) {
-            // Note: n_ctx - 4 here is to match the logic for commandline prompt handling via
+            // Note: (n_ctx - 4) here is to match the logic for commandline prompt handling via
             // --prompt or --file which uses the same value.
             int max_embd_size = n_ctx - 4;
 
@@ -650,6 +650,10 @@ int main(int argc, char ** argv) {
                 n_past += n_eval;
 
                 LOG("n_past = %d\n", n_past);
+                // Display total tokens alongside total time
+                if (n_past % params.token_interval == 0) {
+                    printf("\n\033[31mTokens consumed so far = %d / %d \033[0m\n", n_past, n_ctx);
+                }
             }
 
             if (!embd.empty() && !path_session.empty()) {

examples/server/README.md

@@ -23,7 +23,8 @@ Command line options:
 -   `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`.
 -   `--port`: Set the port to listen. Default: `8080`.
 -   `--path`: path from which to serve static files (default examples/server/public)
--   `--api-key`: Set an api key for request authorization. By default the server responds to every request. With an api key set, the requests must have the Authorization header set with the api key as Bearer token.
+-   `--api-key`: Set an api key for request authorization. By default the server responds to every request. With an api key set, the requests must have the Authorization header set with the api key as Bearer token. May be used multiple times to enable multiple valid keys.
+-   `--api-key-file`: path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access. May be used in conjunction with `--api-key`'s.
 -   `--embedding`: Enable embedding extraction, Default: disabled.
 -   `-np N`, `--parallel N`: Set the number of slots for process requests (default: 1)
 -   `-cb`, `--cont-batching`: enable continuous batching (a.k.a dynamic batching) (default: disabled)
@@ -110,6 +111,10 @@ node index.js
 ```
 
 ## API Endpoints
+- **GET** `/health`: Returns the current state of the server:
+    - `{"status": "loading model"}` if the model is still being loaded.
+    - `{"status": "error"}` if the model failed to load.
+    - `{"status": "ok"}` if the model is successfully loaded and the server is ready for further requests mentioned below.
 
 -   **POST** `/completion`: Given a `prompt`, it returns the predicted completion.
 

examples/server/server.cpp

@@ -39,7 +39,7 @@ using json = nlohmann::json;
 struct server_params
 {
     std::string hostname = "127.0.0.1";
-    std::string api_key;
+    std::vector<std::string> api_keys;
     std::string public_path = "examples/server/public";
     int32_t port = 8080;
     int32_t read_timeout = 600;
@@ -147,15 +147,15 @@ static std::vector<uint8_t> base64_decode(const std::string & encoded_string)
 // parallel
 //
 
-enum ServerState {
-    LOADING_MODEL,  // Server is starting up, model not fully loaded yet
-    READY,          // Server is ready and model is loaded
-    ERROR           // An error occurred, load_model failed
+enum server_state {
+    SERVER_STATE_LOADING_MODEL,  // Server is starting up, model not fully loaded yet
+    SERVER_STATE_READY,          // Server is ready and model is loaded
+    SERVER_STATE_ERROR           // An error occurred, load_model failed
 };
 
 enum task_type {
-    COMPLETION_TASK,
-    CANCEL_TASK
+    TASK_TYPE_COMPLETION,
+    TASK_TYPE_CANCEL,
 };
 
 struct task_server {
@@ -1402,7 +1402,7 @@ struct llama_server_context
         task.data = std::move(data);
         task.infill_mode = infill;
         task.embedding_mode = embedding;
-        task.type = COMPLETION_TASK;
+        task.type = TASK_TYPE_COMPLETION;
         task.multitask_id = multitask_id;
 
         // when a completion task's prompt array is not a singleton, we split it into multiple requests
@@ -1524,7 +1524,7 @@ struct llama_server_context
         std::unique_lock<std::mutex> lock(mutex_tasks);
         task_server task;
         task.id = id_gen++;
-        task.type = CANCEL_TASK;
+        task.type = TASK_TYPE_CANCEL;
         task.target_id = task_id;
         queue_tasks.push_back(task);
         condition_tasks.notify_one();
@@ -1560,7 +1560,7 @@ struct llama_server_context
             queue_tasks.erase(queue_tasks.begin());
             switch (task.type)
             {
-                case COMPLETION_TASK: {
+                case TASK_TYPE_COMPLETION: {
                     llama_client_slot *slot = get_slot(json_value(task.data, "slot_id", -1));
                     if (slot == nullptr)
                     {
@@ -1589,7 +1589,7 @@ struct llama_server_context
                         break;
                     }
                 } break;
-                case CANCEL_TASK: { // release slot linked with the task id
+                case TASK_TYPE_CANCEL: { // release slot linked with the task id
                     for (auto & slot : slots)
                     {
                         if (slot.task_id == task.target_id)
@@ -2021,6 +2021,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
     printf("  --port PORT           port to listen (default  (default: %d)\n", sparams.port);
     printf("  --path PUBLIC_PATH    path from which to serve static files (default %s)\n", sparams.public_path.c_str());
     printf("  --api-key API_KEY     optional api key to enhance server security. If set, requests must include this key for access.\n");
+    printf("  --api-key-file FNAME  path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access.\n");
     printf("  -to N, --timeout N    server read/write timeout in seconds (default: %d)\n", sparams.read_timeout);
     printf("  --embedding           enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled");
     printf("  -np N, --parallel N   number of slots for process requests (default: %d)\n", params.n_parallel);
@@ -2081,7 +2082,28 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
                 invalid_param = true;
                 break;
             }
-            sparams.api_key = argv[i];
+            sparams.api_keys.push_back(argv[i]);
+        }
+        else if (arg == "--api-key-file")
+        {
+            if (++i >= argc)
+            {
+                invalid_param = true;
+                break;
+            }
+            std::ifstream key_file(argv[i]);
+            if (!key_file) {
+                fprintf(stderr, "error: failed to open file '%s'\n", argv[i]);
+                invalid_param = true;
+                break;
+            }
+            std::string key;
+            while (std::getline(key_file, key)) {
+               if (key.size() > 0) {
+                   sparams.api_keys.push_back(key);
+               }
+            }
+            key_file.close();
         }
         else if (arg == "--timeout" || arg == "-to")
         {
@@ -2515,7 +2537,7 @@ json oaicompat_completion_params_parse(
     //
     // https://platform.openai.com/docs/api-reference/chat/create
     llama_sampling_params default_sparams;
-    llama_params["model"]             = json_value(body, "model", std::string("uknown"));
+    llama_params["model"]             = json_value(body, "model", std::string("unknown"));
     llama_params["prompt"]            = format_chatml(body["messages"]); // OpenAI 'messages' to llama.cpp 'prompt'
     llama_params["cache_prompt"]      = json_value(body, "cache_prompt", false);
     llama_params["temperature"]       = json_value(body, "temperature", 0.0);
@@ -2798,24 +2820,30 @@ int main(int argc, char **argv)
 
     httplib::Server svr;
 
-    std::atomic<ServerState> server_state{LOADING_MODEL};
+    std::atomic<server_state> state{SERVER_STATE_LOADING_MODEL};
 
-    svr.set_default_headers({{"Server", "llama.cpp"},
-                             {"Access-Control-Allow-Origin", "*"},
-                             {"Access-Control-Allow-Headers", "content-type"}});
+    svr.set_default_headers({{"Server", "llama.cpp"}});
+
+    // CORS preflight
+    svr.Options(R"(.*)", [](const httplib::Request &req, httplib::Response &res) {
+        res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
+        res.set_header("Access-Control-Allow-Credentials", "true");
+        res.set_header("Access-Control-Allow-Methods", "POST");
+        res.set_header("Access-Control-Allow-Headers", "*");
+    });
 
     svr.Get("/health", [&](const httplib::Request&, httplib::Response& res) {
-        ServerState current_state = server_state.load();
+        server_state current_state = state.load();
         switch(current_state) {
-            case READY:
+            case SERVER_STATE_READY:
                 res.set_content(R"({"status": "ok"})", "application/json");
                 res.status = 200; // HTTP OK
                 break;
-            case LOADING_MODEL:
+            case SERVER_STATE_LOADING_MODEL:
                 res.set_content(R"({"status": "loading model"})", "application/json");
                 res.status = 503; // HTTP Service Unavailable
                 break;
-            case ERROR:
+            case SERVER_STATE_ERROR:
                 res.set_content(R"({"status": "error", "error": "Model failed to load"})", "application/json");
                 res.status = 500; // HTTP Internal Server Error
                 break;
@@ -2881,8 +2909,10 @@ int main(int argc, char **argv)
     log_data["hostname"] = sparams.hostname;
     log_data["port"] = std::to_string(sparams.port);
 
-    if (!sparams.api_key.empty()) {
-        log_data["api_key"] = "api_key: ****" + sparams.api_key.substr(sparams.api_key.length() - 4);
+    if (sparams.api_keys.size() == 1) {
+        log_data["api_key"] = "api_key: ****" + sparams.api_keys[0].substr(sparams.api_keys[0].length() - 4);
+    } else if (sparams.api_keys.size() > 1) {
+        log_data["api_key"] = "api_key: " + std::to_string(sparams.api_keys.size()) + " keys loaded";
     }
 
     LOG_INFO("HTTP server listening", log_data);
@@ -2891,7 +2921,7 @@ int main(int argc, char **argv)
             {
                 if (!svr.listen_after_bind())
                 {
-                    server_state.store(ERROR);
+                    state.store(SERVER_STATE_ERROR);
                     return 1;
                 }
 
@@ -2901,17 +2931,18 @@ int main(int argc, char **argv)
     // load the model
     if (!llama.load_model(params))
     {
-        server_state.store(ERROR);
+        state.store(SERVER_STATE_ERROR);
         return 1;
     } else {
         llama.initialize();
-        server_state.store(READY);
+        state.store(SERVER_STATE_READY);
+        LOG_INFO("model loaded", {});
     }
 
     // Middleware for API key validation
     auto validate_api_key = [&sparams](const httplib::Request &req, httplib::Response &res) -> bool {
         // If API key is not set, skip validation
-        if (sparams.api_key.empty()) {
+        if (sparams.api_keys.empty()) {
             return true;
         }
 
@@ -2920,7 +2951,7 @@ int main(int argc, char **argv)
         std::string prefix = "Bearer ";
         if (auth_header.substr(0, prefix.size()) == prefix) {
             std::string received_api_key = auth_header.substr(prefix.size());
-            if (received_api_key == sparams.api_key) {
+            if (std::find(sparams.api_keys.begin(), sparams.api_keys.end(), received_api_key) != sparams.api_keys.end()) {
                 return true; // API key is valid
             }
         }
@@ -2962,9 +2993,9 @@ int main(int argc, char **argv)
                 return false;
             });
 
-    svr.Get("/props", [&llama](const httplib::Request & /*req*/, httplib::Response &res)
+    svr.Get("/props", [&llama](const httplib::Request & req, httplib::Response &res)
             {
-                res.set_header("Access-Control-Allow-Origin", "*");
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 json data = {
                     { "user_name",      llama.name_user.c_str() },
                     { "assistant_name", llama.name_assistant.c_str() }
@@ -2974,6 +3005,7 @@ int main(int argc, char **argv)
 
     svr.Post("/completion", [&llama, &validate_api_key](const httplib::Request &req, httplib::Response &res)
             {
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 if (!validate_api_key(req, res)) {
                     return;
                 }
@@ -3041,8 +3073,9 @@ int main(int argc, char **argv)
                 }
             });
 
-    svr.Get("/v1/models", [&params](const httplib::Request&, httplib::Response& res)
+    svr.Get("/v1/models", [&params](const httplib::Request& req, httplib::Response& res)
             {
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 std::time_t t = std::time(0);
 
                 json models = {
@@ -3060,9 +3093,11 @@ int main(int argc, char **argv)
                 res.set_content(models.dump(), "application/json; charset=utf-8");
             });
 
+
     // TODO: add mount point without "/v1" prefix -- how?
     svr.Post("/v1/chat/completions", [&llama, &validate_api_key](const httplib::Request &req, httplib::Response &res)
             {
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 if (!validate_api_key(req, res)) {
                     return;
                 }
@@ -3136,6 +3171,7 @@ int main(int argc, char **argv)
 
     svr.Post("/infill", [&llama, &validate_api_key](const httplib::Request &req, httplib::Response &res)
             {
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 if (!validate_api_key(req, res)) {
                     return;
                 }
@@ -3208,6 +3244,7 @@ int main(int argc, char **argv)
 
     svr.Post("/tokenize", [&llama](const httplib::Request &req, httplib::Response &res)
             {
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 const json body = json::parse(req.body);
                 std::vector<llama_token> tokens;
                 if (body.count("content") != 0)
@@ -3220,6 +3257,7 @@ int main(int argc, char **argv)
 
     svr.Post("/detokenize", [&llama](const httplib::Request &req, httplib::Response &res)
             {
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 const json body = json::parse(req.body);
                 std::string content;
                 if (body.count("tokens") != 0)
@@ -3234,6 +3272,7 @@ int main(int argc, char **argv)
 
     svr.Post("/embedding", [&llama](const httplib::Request &req, httplib::Response &res)
             {
+                res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
                 const json body = json::parse(req.body);
                 json prompt;
                 if (body.count("content") != 0)