caching

llm_server/routes/helpers/http.py

@@ -16,7 +16,7 @@ def cache_control(seconds):
         @wraps(f)
         def decorated_function(*args, **kwargs):
             resp = make_response(f(*args, **kwargs))
-            if seconds >= 0:
+            if seconds > 0:
                 resp.headers['Cache-Control'] = f'public, max-age={seconds}'
             else:
                 resp.headers['Cache-Control'] = f'no-store'

llm_server/routes/v1/info.py

@@ -21,7 +21,6 @@ from ..cache import cache
 
 @bp.route('/model', methods=['GET'])
 @cache.cached(timeout=60, query_string=True)
-@cache_control(60)
 def get_model():
     model = get_running_model()
     if not model: