server: introduce API for serving / loading / unloading multiple models (#17470)
* server: add model management and proxy * fix compile error * does this fix windows? * fix windows build * use subprocess.h, better logging * add test * fix windows * feat: Model/Router server architecture WIP * more stable * fix unsafe pointer * also allow terminate loading model * add is_active() * refactor: Architecture improvements * tmp apply upstream fix * address most problems * address thread safety issue * address review comment * add docs (first version) * address review comment * feat: Improved UX for model information, modality interactions etc * chore: update webui build output * refactor: Use only the message data `model` property for displaying model used info * chore: update webui build output * add --models-dir param * feat: New Model Selection UX WIP * chore: update webui build output * feat: Add auto-mic setting * feat: Attachments UX improvements * implement LRU * remove default model path * better --models-dir * add env for args * address review comments * fix compile * refactor: Chat Form Submit component * ad endpoint docs * Merge remote-tracking branch 'webui/allozaur/server_model_management_v1_2' into xsn/server_model_maagement_v1_2 Co-authored-by: Aleksander <aleksander.grygier@gmail.com> * feat: Add copy to clipboard to model name in model info dialog * feat: Model unavailable UI state for model selector * feat: Chat Form Actions UI logic improvements * feat: Auto-select model from last assistant response * chore: update webui build output * expose args and exit_code in API * add note * support extra_args on loading model * allow reusing args if auto_load * typo docs * oai-compat /models endpoint * cleaner * address review comments * feat: Use `model` property for displaying the `repo/model-name` naming format * refactor: Attachments data * chore: update webui build output * refactor: Enum imports * feat: Improve Model Selector responsiveness * chore: update webui build output * refactor: Cleanup * refactor: Cleanup * refactor: Formatters * chore: update webui build output * refactor: Copy To Clipboard Icon component * chore: update webui build output * refactor: Cleanup * chore: update webui build output * refactor: UI badges * chore: update webui build output * refactor: Cleanup * refactor: Cleanup * chore: update webui build output * add --models-allow-extra-args for security * nits * add stdin_file * fix merge * fix: Retrieve lost setting after resolving merge conflict * refactor: DatabaseStore -> DatabaseService * refactor: Database, Conversations & Chat services + stores architecture improvements (WIP) * refactor: Remove redundant settings * refactor: Multi-model business logic WIP * chore: update webui build output * feat: Switching models logic for ChatForm or when regenerating messges + modality detection logic * chore: update webui build output * fix: Add `untrack` inside chat processing info data logic to prevent infinite effect * fix: Regenerate * feat: Remove redundant settigns + rearrange * fix: Audio attachments * refactor: Icons * chore: update webui build output * feat: Model management and selection features WIP * chore: update webui build output * refactor: Improve server properties management * refactor: Icons * chore: update webui build output * feat: Improve model loading/unloading status updates * chore: update webui build output * refactor: Improve API header management via utility functions * remove support for extra args * set hf_repo/docker_repo as model alias when posible * refactor: Remove ConversationsService * refactor: Chat requests abort handling * refactor: Server store * tmp webui build * refactor: Model modality handling * chore: update webui build output * refactor: Processing state reactivity * fix: UI * refactor: Services/Stores syntax + logic improvements Refactors components to access stores directly instead of using exported getter functions. This change centralizes store access and logic, simplifying component code and improving maintainability by reducing the number of exported functions and promoting direct store interaction. Removes exported getter functions from `chat.svelte.ts`, `conversations.svelte.ts`, `models.svelte.ts` and `settings.svelte.ts`. * refactor: Architecture cleanup * feat: Improve statistic badges * feat: Condition available models based on modality + better model loading strategy & UX * docs: Architecture documentation * feat: Update logic for PDF as Image * add TODO for http client * refactor: Enhance model info and attachment handling * chore: update webui build output * refactor: Components naming * chore: update webui build output * refactor: Cleanup * refactor: DRY `getAttachmentDisplayItems` function + fix UI * chore: update webui build output * fix: Modality detection improvement for text-based PDF attachments * refactor: Cleanup * docs: Add info comment * refactor: Cleanup * re * refactor: Cleanup * refactor: Cleanup * feat: Attachment logic & UI improvements * refactor: Constants * feat: Improve UI sidebar background color * chore: update webui build output * refactor: Utils imports + move types to `app.d.ts` * test: Fix Storybook mocks * chore: update webui build output * test: Update Chat Form UI tests * refactor: Tooltip Provider from core layout * refactor: Tests to separate location * decouple server_models from server_routes * test: Move demo test to tests/server * refactor: Remove redundant method * chore: update webui build output * also route anthropic endpoints * fix duplicated arg * fix invalid ptr to shutdown_handler * server : minor * rm unused fn * add ?autoload=true|false query param * refactor: Remove redundant code * docs: Update README documentations + architecture & data flow diagrams * fix: Disable autoload on calling server props for the model * chore: update webui build output * fix ubuntu build * fix: Model status reactivity * fix: Modality detection for MODEL mode * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan-Son Nguyen
GitHub
parent
7733409734
commit
ec18edfcba
178 changed files with 11643 additions and 4356 deletions
|
|
@ -1,5 +1,6 @@
|
|||
#include "server-context.h"
|
||||
#include "server-http.h"
|
||||
#include "server-models.h"
|
||||
|
||||
#include "arg.h"
|
||||
#include "common.h"
|
||||
|
|
@ -47,16 +48,16 @@ static server_http_context::handler_t ex_wrapper(server_http_context::handler_t
|
|||
json error_data = format_error_response(message, ERROR_TYPE_SERVER);
|
||||
res->status = json_value(error_data, "code", 500);
|
||||
res->data = safe_json_to_str({{ "error", error_data }});
|
||||
LOG_WRN("got exception: %s\n", res->data.c_str());
|
||||
SRV_WRN("got exception: %s\n", res->data.c_str());
|
||||
} catch (const std::exception & e) {
|
||||
LOG_ERR("got another exception: %s | while hanlding exception: %s\n", e.what(), message.c_str());
|
||||
SRV_ERR("got another exception: %s | while handling exception: %s\n", e.what(), message.c_str());
|
||||
res->data = "Internal Server Error";
|
||||
}
|
||||
return res;
|
||||
};
|
||||
}
|
||||
|
||||
int main(int argc, char ** argv) {
|
||||
int main(int argc, char ** argv, char ** envp) {
|
||||
// own arguments required by this example
|
||||
common_params params;
|
||||
|
||||
|
|
@ -75,6 +76,11 @@ int main(int argc, char ** argv) {
|
|||
params.kv_unified = true;
|
||||
}
|
||||
|
||||
// for consistency between server router mode and single-model mode, we set the same model name as alias
|
||||
if (params.model_alias.empty() && !params.model.name.empty()) {
|
||||
params.model_alias = params.model.name;
|
||||
}
|
||||
|
||||
common_init();
|
||||
|
||||
// struct that contains llama context and inference
|
||||
|
|
@ -101,6 +107,42 @@ int main(int argc, char ** argv) {
|
|||
// register API routes
|
||||
server_routes routes(params, ctx_server, [&ctx_http]() { return ctx_http.is_ready.load(); });
|
||||
|
||||
bool is_router_server = params.model.path.empty();
|
||||
std::optional<server_models_routes> models_routes{};
|
||||
if (is_router_server) {
|
||||
// setup server instances manager
|
||||
models_routes.emplace(params, argc, argv, envp);
|
||||
|
||||
// proxy handlers
|
||||
// note: routes.get_health stays the same
|
||||
routes.get_metrics = models_routes->proxy_get;
|
||||
routes.post_props = models_routes->proxy_post;
|
||||
routes.get_api_show = models_routes->proxy_get;
|
||||
routes.post_completions = models_routes->proxy_post;
|
||||
routes.post_completions_oai = models_routes->proxy_post;
|
||||
routes.post_chat_completions = models_routes->proxy_post;
|
||||
routes.post_anthropic_messages = models_routes->proxy_post;
|
||||
routes.post_anthropic_count_tokens = models_routes->proxy_post;
|
||||
routes.post_infill = models_routes->proxy_post;
|
||||
routes.post_embeddings = models_routes->proxy_post;
|
||||
routes.post_embeddings_oai = models_routes->proxy_post;
|
||||
routes.post_rerank = models_routes->proxy_post;
|
||||
routes.post_tokenize = models_routes->proxy_post;
|
||||
routes.post_detokenize = models_routes->proxy_post;
|
||||
routes.post_apply_template = models_routes->proxy_post;
|
||||
routes.get_lora_adapters = models_routes->proxy_get;
|
||||
routes.post_lora_adapters = models_routes->proxy_post;
|
||||
routes.get_slots = models_routes->proxy_get;
|
||||
routes.post_slots = models_routes->proxy_post;
|
||||
|
||||
// custom routes for router
|
||||
routes.get_props = models_routes->get_router_props;
|
||||
routes.get_models = models_routes->get_router_models;
|
||||
ctx_http.post("/models/load", ex_wrapper(models_routes->post_router_models_load));
|
||||
ctx_http.post("/models/unload", ex_wrapper(models_routes->post_router_models_unload));
|
||||
ctx_http.post("/models/status", ex_wrapper(models_routes->post_router_models_status));
|
||||
}
|
||||
|
||||
ctx_http.get ("/health", ex_wrapper(routes.get_health)); // public endpoint (no API key check)
|
||||
ctx_http.get ("/v1/health", ex_wrapper(routes.get_health)); // public endpoint (no API key check)
|
||||
ctx_http.get ("/metrics", ex_wrapper(routes.get_metrics));
|
||||
|
|
@ -140,43 +182,69 @@ int main(int argc, char ** argv) {
|
|||
// Start the server
|
||||
//
|
||||
|
||||
// setup clean up function, to be called before exit
|
||||
auto clean_up = [&ctx_http, &ctx_server]() {
|
||||
SRV_INF("%s: cleaning up before exit...\n", __func__);
|
||||
ctx_http.stop();
|
||||
ctx_server.terminate();
|
||||
llama_backend_free();
|
||||
};
|
||||
std::function<void()> clean_up;
|
||||
|
||||
// start the HTTP server before loading the model to be able to serve /health requests
|
||||
if (!ctx_http.start()) {
|
||||
clean_up();
|
||||
LOG_ERR("%s: exiting due to HTTP server error\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
if (is_router_server) {
|
||||
LOG_INF("%s: starting router server, no model will be loaded in this process\n", __func__);
|
||||
|
||||
// load the model
|
||||
LOG_INF("%s: loading model\n", __func__);
|
||||
clean_up = [&models_routes]() {
|
||||
SRV_INF("%s: cleaning up before exit...\n", __func__);
|
||||
if (models_routes.has_value()) {
|
||||
models_routes->models.unload_all();
|
||||
}
|
||||
llama_backend_free();
|
||||
};
|
||||
|
||||
if (!ctx_server.load_model(params)) {
|
||||
clean_up();
|
||||
if (ctx_http.thread.joinable()) {
|
||||
ctx_http.thread.join();
|
||||
if (!ctx_http.start()) {
|
||||
clean_up();
|
||||
LOG_ERR("%s: exiting due to HTTP server error\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
LOG_ERR("%s: exiting due to model loading error\n", __func__);
|
||||
return 1;
|
||||
ctx_http.is_ready.store(true);
|
||||
|
||||
shutdown_handler = [&](int) {
|
||||
ctx_http.stop();
|
||||
};
|
||||
|
||||
} else {
|
||||
// setup clean up function, to be called before exit
|
||||
clean_up = [&ctx_http, &ctx_server]() {
|
||||
SRV_INF("%s: cleaning up before exit...\n", __func__);
|
||||
ctx_http.stop();
|
||||
ctx_server.terminate();
|
||||
llama_backend_free();
|
||||
};
|
||||
|
||||
// start the HTTP server before loading the model to be able to serve /health requests
|
||||
if (!ctx_http.start()) {
|
||||
clean_up();
|
||||
LOG_ERR("%s: exiting due to HTTP server error\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
|
||||
// load the model
|
||||
LOG_INF("%s: loading model\n", __func__);
|
||||
|
||||
if (!ctx_server.load_model(params)) {
|
||||
clean_up();
|
||||
if (ctx_http.thread.joinable()) {
|
||||
ctx_http.thread.join();
|
||||
}
|
||||
LOG_ERR("%s: exiting due to model loading error\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
|
||||
ctx_server.init();
|
||||
ctx_http.is_ready.store(true);
|
||||
|
||||
LOG_INF("%s: model loaded\n", __func__);
|
||||
|
||||
shutdown_handler = [&](int) {
|
||||
// this will unblock start_loop()
|
||||
ctx_server.terminate();
|
||||
};
|
||||
}
|
||||
|
||||
ctx_server.init();
|
||||
ctx_http.is_ready.store(true);
|
||||
|
||||
LOG_INF("%s: model loaded\n", __func__);
|
||||
|
||||
shutdown_handler = [&](int) {
|
||||
// this will unblock start_loop()
|
||||
ctx_server.terminate();
|
||||
};
|
||||
|
||||
// TODO: refactor in common/console
|
||||
#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__))
|
||||
struct sigaction sigint_action;
|
||||
|
|
@ -192,16 +260,39 @@ int main(int argc, char ** argv) {
|
|||
SetConsoleCtrlHandler(reinterpret_cast<PHANDLER_ROUTINE>(console_ctrl_handler), true);
|
||||
#endif
|
||||
|
||||
LOG_INF("%s: server is listening on %s\n", __func__, ctx_http.listening_address.c_str());
|
||||
LOG_INF("%s: starting the main loop...\n", __func__);
|
||||
// this call blocks the main thread until ctx_server.terminate() is called
|
||||
ctx_server.start_loop();
|
||||
if (is_router_server) {
|
||||
LOG_INF("%s: router server is listening on %s\n", __func__, ctx_http.listening_address.c_str());
|
||||
LOG_INF("%s: NOTE: router mode is experimental\n", __func__);
|
||||
LOG_INF("%s: it is not recommended to use this mode in untrusted environments\n", __func__);
|
||||
if (ctx_http.thread.joinable()) {
|
||||
ctx_http.thread.join(); // keep the main thread alive
|
||||
}
|
||||
|
||||
clean_up();
|
||||
if (ctx_http.thread.joinable()) {
|
||||
ctx_http.thread.join();
|
||||
// when the HTTP server stops, clean up and exit
|
||||
clean_up();
|
||||
} else {
|
||||
LOG_INF("%s: server is listening on %s\n", __func__, ctx_http.listening_address.c_str());
|
||||
LOG_INF("%s: starting the main loop...\n", __func__);
|
||||
|
||||
// optionally, notify router server that this instance is ready
|
||||
const char * router_port = std::getenv("LLAMA_SERVER_ROUTER_PORT");
|
||||
std::thread monitor_thread;
|
||||
if (router_port != nullptr) {
|
||||
monitor_thread = server_models::setup_child_server(params, std::atoi(router_port), params.model_alias, shutdown_handler);
|
||||
}
|
||||
|
||||
// this call blocks the main thread until queue_tasks.terminate() is called
|
||||
ctx_server.start_loop();
|
||||
|
||||
clean_up();
|
||||
if (ctx_http.thread.joinable()) {
|
||||
ctx_http.thread.join();
|
||||
}
|
||||
if (monitor_thread.joinable()) {
|
||||
monitor_thread.join();
|
||||
}
|
||||
llama_memory_breakdown_print(ctx_server.get_llama_context());
|
||||
}
|
||||
llama_memory_breakdown_print(ctx_server.get_llama_context());
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue