happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

server : minor

This commit is contained in:
Georgi Gerganov 2025-12-01 13:35:40 +02:00
parent 4a1c05c383
commit d182544c99
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
2 changed files with 13 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
tools/server/server-models.cpp
View File

@ -4,6 +4,7 @@
#include "download.h"
#include <cpp-httplib/httplib.h>
#include <sheredom/subprocess.h>
#include <functional>
#include <thread>
@ -12,7 +13,6 @@
#include <cstring>
#include <atomic>
#include <chrono>
#include <unordered_set>
#ifdef _WIN32
#include <winsock2.h>
@ -84,7 +84,7 @@ static std::vector<local_model> list_local_models(const std::string & dir) {
}
std::vector<local_model> models;
auto scan_subdir = [&models](const std::string & subdir_path, const std::string name) {
auto scan_subdir = [&models](const std::string & subdir_path, const std::string & name) {
auto files = fs_list(subdir_path, false);
common_file_info model_file;
common_file_info first_shard_file;
@ -292,6 +292,7 @@ static std::vector<char *> to_char_ptr_array(const std::vector<std::string> & ve
std::vector<server_model_meta> server_models::get_all_meta() {
std::lock_guard<std::mutex> lk(mutex);
std::vector<server_model_meta> result;
result.reserve(mapping.size());
for (const auto & [name, inst] : mapping) {
result.push_back(inst.meta);
}
@ -363,7 +364,7 @@ void server_models::load(const std::string & name, bool auto_load) {
inst.subproc = std::make_shared<subprocess_s>();
{
std::string exec_path = get_server_exec_path().string();
//std::string exec_path = get_server_exec_path().string();
SRV_INF("spawning server instance with name=%s on port %d\n", inst.meta.name.c_str(), inst.meta.port);
std::vector<std::string> child_args;

18
tools/server/server-models.h
View File

@ -3,9 +3,6 @@
#include "common.h"
#include "server-http.h"
#include <sheredom/subprocess.h>
#include <queue>
#include <mutex>
#include <condition_variable>
#include <functional>
@ -30,13 +27,14 @@ enum server_model_status {
static server_model_status server_model_status_from_string(const std::string & status_str) {
if (status_str == "unloaded") {
return SERVER_MODEL_STATUS_UNLOADED;
} else if (status_str == "loading") {
return SERVER_MODEL_STATUS_LOADING;
} else if (status_str == "loaded") {
return SERVER_MODEL_STATUS_LOADED;
} else {
throw std::runtime_error("invalid server model status");
}
if (status_str == "loading") {
return SERVER_MODEL_STATUS_LOADING;
}
if (status_str == "loaded") {
return SERVER_MODEL_STATUS_LOADED;
}
throw std::runtime_error("invalid server model status");
}
static std::string server_model_status_to_string(server_model_status status) {
@ -68,6 +66,8 @@ struct server_model_meta {
}
};
struct subprocess_s;
struct server_models {
private:
struct instance_t {