diff --git a/python/sglang/srt/model_executor/cuda_graph_runner.py b/python/sglang/srt/model_executor/cuda_graph_runner.py index 978a772f1..fc892ddf0 100644 --- a/python/sglang/srt/model_executor/cuda_graph_runner.py +++ b/python/sglang/srt/model_executor/cuda_graph_runner.py @@ -237,6 +237,7 @@ class CudaGraphRunner: "1. disable cuda graph by --disable-cuda-graph\n" "2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)\n" "3. disable torch compile by not using --enable-torch-compile\n" + "4. set --cuda-graph-max-bs to a smaller value (e.g., 32)\n" "Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose \n" )