daemon.py

@@ -10,7 +10,7 @@ from llm_server.config.load import load_config, parse_backends
 from llm_server.custom_redis import redis
 from llm_server.database.create import create_db
 from llm_server.routes.queue import priority_queue
-from llm_server.routes.v1.generate_stats import generate_stats
+from llm_server.routes.v2.generate_stats import generate_stats
 from llm_server.workers.threader import start_background
 
 script_path = os.path.dirname(os.path.realpath(__file__))

llm_server/workers/threader.py

@@ -4,7 +4,7 @@ from threading import Thread
 from llm_server import opts
 from llm_server.cluster.stores import redis_running_models
 from llm_server.cluster.worker import cluster_worker
-from llm_server.routes.v1.generate_stats import generate_stats
+from llm_server.routes.v2.generate_stats import generate_stats
 from llm_server.workers.inferencer import start_workers
 from llm_server.workers.mainer import main_background_thread
 from llm_server.workers.moderator import start_moderation_workers

server.py

@@ -21,7 +21,7 @@ from llm_server.database.create import create_db
 from llm_server.pre_fork import server_startup
 from llm_server.routes.openai import openai_bp
 from llm_server.routes.server_error import handle_server_error
-from llm_server.routes.v1 import bp
+from llm_server.routes.v2 import bp
 from llm_server.sock import init_socketio
 
 # TODO: per-backend workers
@@ -65,7 +65,7 @@ from llm_server.helpers import auto_set_base_client_api
 from llm_server.llm.vllm.info import vllm_info
 from llm_server.custom_redis import flask_cache
 from llm_server.llm import redis
-from llm_server.routes.v1.generate_stats import generate_stats
+from llm_server.routes.v2.generate_stats import generate_stats
 
 app = Flask(__name__)
 init_socketio(app)