diff --git a/fastdeploy/engine/args_utils.py b/fastdeploy/engine/args_utils.py index 81d980bf80..eeef7930f1 100644 --- a/fastdeploy/engine/args_utils.py +++ b/fastdeploy/engine/args_utils.py @@ -268,7 +268,7 @@ class EngineArgs: """ Flag to enable prefix caching. """ - enable_output_caching: bool = True + enable_output_caching: bool = False """ Flag to enable kv cache for output tokens, only valid in V1 scheduler. """