server : add LOG_INFO when model is successfully loaded (#4881)

* added /health endpoint to the server

* added comments on the additional /health endpoint

* Better handling of server state

When the model is being loaded, the server state is `LOADING_MODEL`. If model-loading fails, the server state becomes `ERROR`, otherwise it becomes `READY`. The `/health` endpoint provides more granular messages now according to the server_state value.

* initialized server_state

* fixed a typo

* starting http server before initializing the model

* Update server.cpp

* Update server.cpp

* fixes

* fixes

* fixes

* made ServerState atomic and turned two-line spaces into one-line

* updated `server` readme to document the `/health` endpoint too

* used LOG_INFO after successful model loading

.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 }}

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

@@ -110,6 +110,10 @@ 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

@@ -26,6 +26,7 @@
 #include <mutex>
 #include <chrono>
 #include <condition_variable>
+#include <atomic>
 
 #ifndef SERVER_VERBOSE
 #define SERVER_VERBOSE 1
@@ -146,9 +147,15 @@ static std::vector<uint8_t> base64_decode(const std::string & encoded_string)
 // parallel
 //
 
+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 {
@@ -1395,7 +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
@@ -1517,7 +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();
@@ -1553,7 +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)
                     {
@@ -1582,7 +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)
@@ -2453,7 +2460,6 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
     }
 }
 
-
 static std::string random_string()
 {
     static const std::string str("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");
@@ -2509,7 +2515,7 @@ 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);
@@ -2790,15 +2796,118 @@ int main(int argc, char **argv)
                                 {"system_info", llama_print_system_info()},
                             });
 
-    // load the model
-    if (!llama.load_model(params))
+    httplib::Server svr;
+
+    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.Get("/health", [&](const httplib::Request&, httplib::Response& res) {
+        server_state current_state = state.load();
+        switch(current_state) {
+            case SERVER_STATE_READY:
+                res.set_content(R"({"status": "ok"})", "application/json");
+                res.status = 200; // HTTP OK
+                break;
+            case SERVER_STATE_LOADING_MODEL:
+                res.set_content(R"({"status": "loading model"})", "application/json");
+                res.status = 503; // HTTP Service Unavailable
+                break;
+            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;
+        }
+    });
+
+    svr.set_logger(log_server_request);
+
+    svr.set_exception_handler([](const httplib::Request &, httplib::Response &res, std::exception_ptr ep)
+            {
+                const char fmt[] = "500 Internal Server Error\n%s";
+                char buf[BUFSIZ];
+                try
+                {
+                    std::rethrow_exception(std::move(ep));
+                }
+                catch (std::exception &e)
+                {
+                    snprintf(buf, sizeof(buf), fmt, e.what());
+                }
+                catch (...)
+                {
+                    snprintf(buf, sizeof(buf), fmt, "Unknown Exception");
+                }
+                res.set_content(buf, "text/plain; charset=utf-8");
+                res.status = 500;
+            });
+
+    svr.set_error_handler([](const httplib::Request &, httplib::Response &res)
+            {
+                if (res.status == 401)
+                {
+                    res.set_content("Unauthorized", "text/plain; charset=utf-8");
+                }
+                if (res.status == 400)
+                {
+                    res.set_content("Invalid request", "text/plain; charset=utf-8");
+                }
+                else if (res.status == 404)
+                {
+                    res.set_content("File Not Found", "text/plain; charset=utf-8");
+                    res.status = 404;
+                }
+            });
+
+    // set timeouts and change hostname and port
+    svr.set_read_timeout (sparams.read_timeout);
+    svr.set_write_timeout(sparams.write_timeout);
+
+    if (!svr.bind_to_port(sparams.hostname, sparams.port))
     {
+        fprintf(stderr, "\ncouldn't bind to server socket: hostname=%s port=%d\n\n", sparams.hostname.c_str(), sparams.port);
         return 1;
     }
 
-    llama.initialize();
+    // Set the base directory for serving static files
+    svr.set_base_dir(sparams.public_path);
 
-    httplib::Server svr;
+    // to make it ctrl+clickable:
+    LOG_TEE("\nllama server listening at http://%s:%d\n\n", sparams.hostname.c_str(), sparams.port);
+
+    std::unordered_map<std::string, std::string> log_data;
+    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);
+    }
+
+    LOG_INFO("HTTP server listening", log_data);
+    // run the HTTP server in a thread - see comment below
+    std::thread t([&]()
+            {
+                if (!svr.listen_after_bind())
+                {
+                    state.store(SERVER_STATE_ERROR);
+                    return 1;
+                }
+
+                return 0;
+            });
+
+    // load the model
+    if (!llama.load_model(params))
+    {
+        state.store(SERVER_STATE_ERROR);
+        return 1;
+    } else {
+        llama.initialize();
+        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 {
@@ -2826,10 +2935,6 @@ int main(int argc, char **argv)
         return false;
     };
 
-    svr.set_default_headers({{"Server", "llama.cpp"},
-                             {"Access-Control-Allow-Origin", "*"},
-                             {"Access-Control-Allow-Headers", "content-type"}});
-
     // this is only called if no index.html is found in the public --path
     svr.Get("/", [](const httplib::Request &, httplib::Response &res)
             {
@@ -2937,8 +3042,6 @@ int main(int argc, char **argv)
                 }
             });
 
-
-
     svr.Get("/v1/models", [&params](const httplib::Request&, httplib::Response& res)
             {
                 std::time_t t = std::time(0);
@@ -3157,81 +3260,6 @@ int main(int argc, char **argv)
                 return res.set_content(result.result_json.dump(), "application/json; charset=utf-8");
             });
 
-    svr.set_logger(log_server_request);
-
-    svr.set_exception_handler([](const httplib::Request &, httplib::Response &res, std::exception_ptr ep)
-            {
-                const char fmt[] = "500 Internal Server Error\n%s";
-                char buf[BUFSIZ];
-                try
-                {
-                    std::rethrow_exception(std::move(ep));
-                }
-                catch (std::exception &e)
-                {
-                    snprintf(buf, sizeof(buf), fmt, e.what());
-                }
-                catch (...)
-                {
-                    snprintf(buf, sizeof(buf), fmt, "Unknown Exception");
-                }
-                res.set_content(buf, "text/plain; charset=utf-8");
-                res.status = 500;
-            });
-
-    svr.set_error_handler([](const httplib::Request &, httplib::Response &res)
-            {
-                if (res.status == 401)
-                {
-                    res.set_content("Unauthorized", "text/plain; charset=utf-8");
-                }
-                if (res.status == 400)
-                {
-                    res.set_content("Invalid request", "text/plain; charset=utf-8");
-                }
-                else if (res.status == 404)
-                {
-                    res.set_content("File Not Found", "text/plain; charset=utf-8");
-                    res.status = 404;
-                }
-            });
-
-    // set timeouts and change hostname and port
-    svr.set_read_timeout (sparams.read_timeout);
-    svr.set_write_timeout(sparams.write_timeout);
-
-    if (!svr.bind_to_port(sparams.hostname, sparams.port))
-    {
-        fprintf(stderr, "\ncouldn't bind to server socket: hostname=%s port=%d\n\n", sparams.hostname.c_str(), sparams.port);
-        return 1;
-    }
-
-    // Set the base directory for serving static files
-    svr.set_base_dir(sparams.public_path);
-
-    // to make it ctrl+clickable:
-    LOG_TEE("\nllama server listening at http://%s:%d\n\n", sparams.hostname.c_str(), sparams.port);
-
-    std::unordered_map<std::string, std::string> log_data;
-    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);
-    }
-
-    LOG_INFO("HTTP server listening", log_data);
-    // run the HTTP server in a thread - see comment below
-    std::thread t([&]()
-            {
-                if (!svr.listen_after_bind())
-                {
-                    return 1;
-                }
-
-                return 0;
-            });
-
     // GG: if I put the main loop inside a thread, it crashes on the first request when build in Debug!?
     //     "Bus error: 10" - this is on macOS, it does not crash on Linux
     //std::thread t2([&]()

ggml-cuda.cu

@@ -10184,8 +10184,8 @@ static void ggml_backend_cuda_buffer_set_tensor(ggml_backend_buffer_t buffer, gg
 
     ggml_cuda_set_device(ctx->device);
     CUDA_CHECK(cudaDeviceSynchronize());
-
     CUDA_CHECK(cudaMemcpy((char *)tensor->data + offset, data, size, cudaMemcpyHostToDevice));
+    CUDA_CHECK(cudaDeviceSynchronize());
 }
 
 static void ggml_backend_cuda_buffer_get_tensor(ggml_backend_buffer_t buffer, const ggml_tensor * tensor, void * data, size_t offset, size_t size) {

ggml-metal.m

@@ -1067,6 +1067,10 @@ bool ggml_metal_graph_compute(
                     GGML_ASSERT(!"unsupported op");
                 }
 
+#ifndef GGML_METAL_NDEBUG
+                [encoder pushDebugGroup:[NSString stringWithCString:ggml_op_desc(dst) encoding:NSUTF8StringEncoding]];
+#endif
+
                 const int64_t  ne00 = src0 ? src0->ne[0] : 0;
                 const int64_t  ne01 = src0 ? src0->ne[1] : 0;
                 const int64_t  ne02 = src0 ? src0->ne[2] : 0;
@@ -2423,6 +2427,10 @@ bool ggml_metal_graph_compute(
                             GGML_ASSERT(false);
                         }
                 }
+
+#ifndef GGML_METAL_NDEBUG
+                [encoder popDebugGroup];
+#endif
             }
 
             if (encoder != nil) {

ggml.c

@@ -132,7 +132,7 @@ void ggml_print_backtrace(void) {
             "-ex", "bt -frame-info source-and-location",
             "-ex", "detach",
             "-ex", "quit",
-            NULL);
+            (char *) NULL);
     } else {
         waitpid(pid, NULL, 0);
     }
@@ -4311,13 +4311,13 @@ struct ggml_tensor * ggml_set_2d_inplace(
 static struct ggml_tensor * ggml_cpy_impl(
         struct ggml_context * ctx,
         struct ggml_tensor  * a,
-        struct ggml_tensor  * b,
-        bool inplace) {
+        struct ggml_tensor  * b) {
     GGML_ASSERT(ggml_nelements(a) == ggml_nelements(b));
 
     bool is_node = false;
 
-    if (!inplace && (a->grad || b->grad)) {
+    if (a->grad || b->grad) {
+        // inplace is false and either one have a grad
         is_node = true;
     }
 
@@ -4341,29 +4341,21 @@ struct ggml_tensor * ggml_cpy(
         struct ggml_context * ctx,
         struct ggml_tensor * a,
         struct ggml_tensor * b) {
-    return ggml_cpy_impl(ctx, a, b, false);
-}
-
-struct ggml_tensor * ggml_cpy_inplace(
-        struct ggml_context * ctx,
-        struct ggml_tensor * a,
-        struct ggml_tensor * b) {
-    return ggml_cpy_impl(ctx, a, b, true);
+    return ggml_cpy_impl(ctx, a, b);
 }
 
 // ggml_cont
 
 static struct ggml_tensor * ggml_cont_impl(
         struct ggml_context * ctx,
-        struct ggml_tensor  * a,
-        bool inplace) {
+        struct ggml_tensor  * a) {
     bool is_node = false;
 
-    if (!inplace && a->grad) {
+    if (a->grad) {
         is_node = true;
     }
 
-    struct ggml_tensor * result = inplace ? ggml_view_tensor(ctx, a) : ggml_dup_tensor(ctx, a);
+    struct ggml_tensor * result = ggml_dup_tensor(ctx, a);
     ggml_format_name(result, "%s (cont)", a->name);
 
     result->op   = GGML_OP_CONT;
@@ -4376,13 +4368,7 @@ static struct ggml_tensor * ggml_cont_impl(
 struct ggml_tensor * ggml_cont(
         struct ggml_context * ctx,
         struct ggml_tensor * a) {
-    return ggml_cont_impl(ctx, a, false);
-}
-
-struct ggml_tensor * ggml_cont_inplace(
-        struct ggml_context * ctx,
-        struct ggml_tensor * a) {
-    return ggml_cont_impl(ctx, a, true);
+    return ggml_cont_impl(ctx, a);
 }
 
 // make contiguous, with new shape

ggml.h

@@ -218,7 +218,9 @@
 #define GGML_MAX_PARAMS         2048
 #define GGML_MAX_CONTEXTS       64
 #define GGML_MAX_SRC            10
+#ifndef GGML_MAX_NAME
 #define GGML_MAX_NAME           64
+#endif
 #define GGML_MAX_OP_PARAMS      64
 #define GGML_DEFAULT_N_THREADS  4
 #define GGML_DEFAULT_GRAPH_SIZE 2048
@@ -1161,22 +1163,11 @@ extern "C" {
             struct ggml_tensor  * a,
             struct ggml_tensor  * b);
 
-    // a -> b, in-place, return view(b)
-    GGML_API struct ggml_tensor * ggml_cpy_inplace(
-            struct ggml_context * ctx,
-            struct ggml_tensor  * a,
-            struct ggml_tensor  * b);
-
     // make contiguous
     GGML_API struct ggml_tensor * ggml_cont(
             struct ggml_context * ctx,
             struct ggml_tensor  * a);
 
-    // make contiguous, in-place
-    GGML_API struct ggml_tensor * ggml_cont_inplace(
-            struct ggml_context * ctx,
-            struct ggml_tensor  * a);
-
     // make contiguous, with new shape
     GGML_API struct ggml_tensor * ggml_cont_1d(
             struct ggml_context * ctx,

llama.cpp

@@ -3146,7 +3146,15 @@ static void llm_load_print_meta(llama_model_loader & ml, llama_model & model) {
     LLAMA_LOG_INFO("%s: rope_finetuned   = %s\n",     __func__, hparams.rope_finetuned ? "yes" : "unknown");
     LLAMA_LOG_INFO("%s: model type       = %s\n",     __func__, llama_model_type_name(model.type));
     LLAMA_LOG_INFO("%s: model ftype      = %s\n",     __func__, llama_model_ftype_name(model.ftype).c_str());
-    LLAMA_LOG_INFO("%s: model params     = %.2f B\n", __func__, ml.n_elements*1e-9);
+    if (ml.n_elements >= 1e12) {
+        LLAMA_LOG_INFO("%s: model params     = %.2f T\n", __func__, ml.n_elements*1e-12);
+    } else if (ml.n_elements >= 1e9) {
+        LLAMA_LOG_INFO("%s: model params     = %.2f B\n", __func__, ml.n_elements*1e-9);
+    } else if (ml.n_elements >= 1e6) {
+        LLAMA_LOG_INFO("%s: model params     = %.2f M\n", __func__, ml.n_elements*1e-6);
+    } else {
+        LLAMA_LOG_INFO("%s: model params     = %.2f K\n", __func__, ml.n_elements*1e-3);
+    }
     if (ml.n_bytes < GiB) {
         LLAMA_LOG_INFO("%s: model size       = %.2f MiB (%.2f BPW) \n", __func__, ml.n_bytes/1024.0/1024.0,        ml.n_bytes*8.0/ml.n_elements);
     } else {
@@ -10913,7 +10921,7 @@ void llama_print_timings(struct llama_context * ctx) {
             __func__, timings.t_p_eval_ms, timings.n_p_eval, timings.t_p_eval_ms / timings.n_p_eval, 1e3 / timings.t_p_eval_ms * timings.n_p_eval);
     LLAMA_LOG_INFO("%s:        eval time = %10.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
             __func__, timings.t_eval_ms, timings.n_eval, timings.t_eval_ms / timings.n_eval, 1e3 / timings.t_eval_ms * timings.n_eval);
-    LLAMA_LOG_INFO("%s:       total time = %10.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms));
+    LLAMA_LOG_INFO("%s:       total time = %10.2f ms / %5d tokens\n", __func__, (timings.t_end_ms - timings.t_start_ms), (timings.n_p_eval + timings.n_eval));
 }
 
 void llama_reset_timings(struct llama_context * ctx) {

scripts/sync-ggml.last

@@ -1 +1 @@
-f96711108d55bdbbd277e6be07204dce6a94fb93
+979cc23b345006504cfc1f67c0fdf627805e3319