Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '584d674be622fbf1578694ada6e62eebedbfd377' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/nix-flake-update.yml
#	Makefile
#	Package.swift
#	ggml-cuda.cu
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo
2024-01-14 16:29:44 +08:00
parent bd77a48037 584d674be6
commit dc7bc0cb50
31 changed files with 2138 additions and 386 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/server/README.md
+6 -1
View File
@@ -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
+174 -107
View File
@@ -27,6 +27,7 @@
#include <mutex>
#include <chrono>
#include <condition_variable>
#include <atomic>
#ifndef SERVER_VERBOSE
#define SERVER_VERBOSE 1
@@ -39,7 +40,7 @@ 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;
@@ -147,9 +148,15 @@ 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 {
@@ -1396,11 +1403,11 @@ 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
if (task.data.at("prompt").size() > 1)
if (task.data.count("prompt") && task.data.at("prompt").size() > 1)
{
lock.unlock(); // entering new func scope
return split_multiprompt_task(task);
@@ -1518,7 +1525,7 @@ 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();
@@ -1554,7 +1561,7 @@ 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)
{
@@ -1571,9 +1578,9 @@ struct llama_server_context
slot->reset();
slot->infill = task.infill_mode;
slot->embedding = task.embedding_mode;
slot->task_id = task.id;
slot->infill = task.infill_mode;
slot->embedding = task.embedding_mode;
slot->task_id = task.id;
slot->multitask_id = task.multitask_id;
if (!launch_slot_with_data(slot, task.data))
@@ -1583,7 +1590,7 @@ 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)
@@ -1725,7 +1732,8 @@ struct llama_server_context
const bool has_prompt = slot.prompt.is_array() || (slot.prompt.is_string() && !slot.prompt.get<std::string>().empty()) || !slot.images.empty();
// empty prompt passed -> release the slot and send empty response
if (slot.state == IDLE && slot.command == LOAD_PROMPT && !has_prompt)
// note: infill mode allows empty prompt
if (slot.state == IDLE && slot.command == LOAD_PROMPT && !has_prompt && !slot.infill)
{
slot.release();
slot.print_timings();
@@ -2015,6 +2023,7 @@ 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);
@@ -2075,7 +2084,28 @@ 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")
{
@@ -2454,7 +2484,6 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
}
}
static std::string random_string()
{
static const std::string str("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz");
@@ -2510,7 +2539,7 @@ 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);
@@ -2582,8 +2611,8 @@ static json format_final_response_oaicompat(const json &request, const task_resu
{"object", streaming ? "chat.completion.chunk" : "chat.completion"},
{"usage",
json{{"completion_tokens", num_tokens_predicted},
{"prompt_tokens", num_prompt_tokens},
{"total_tokens", num_tokens_predicted + num_prompt_tokens}}},
{"prompt_tokens", num_prompt_tokens},
{"total_tokens", num_tokens_predicted + num_prompt_tokens}}},
{"id", gen_chatcmplid()}};
if (server_verbose) {
@@ -2791,20 +2820,131 @@ 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"}});
// 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) {
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_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);
// 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 {
// If API key is not set, skip validation
if (sparams.api_key.empty()) {
if (sparams.api_keys.empty()) {
return true;
}
@@ -2813,7 +2953,7 @@ 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
}
}
@@ -2827,10 +2967,6 @@ 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)
{
@@ -2859,9 +2995,9 @@ 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() }
@@ -2871,6 +3007,7 @@ 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;
}
@@ -2938,10 +3075,9 @@ 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 = {
@@ -2959,9 +3095,11 @@ 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;
}
@@ -3035,6 +3173,7 @@ 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;
}
@@ -3107,6 +3246,7 @@ 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)
@@ -3119,6 +3259,7 @@ 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)
@@ -3133,6 +3274,7 @@ 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)
@@ -3158,81 +3300,6 @@ 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([&]()