diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index ba91cd2ac..718208959 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -323,6 +323,9 @@ class ServerArgs: assert ( not self.enable_dp_attention ), "DeepEP MoE `auto` mode is not supported with DP Attention." + if self.deepep_mode == "normal": + logger.warning("Cuda graph is disabled because deepep_mode=`normal`") + self.disable_cuda_graph = True self.ep_size = self.tp_size self.enable_sp_layernorm = ( self.dp_size < self.tp_size if self.enable_dp_attention else True