diff --git a/python/sglang/srt/layers/attention/attention_registry.py b/python/sglang/srt/layers/attention/attention_registry.py
index 9020e5260..2353c1599 100644
--- a/python/sglang/srt/layers/attention/attention_registry.py
+++ b/python/sglang/srt/layers/attention/attention_registry.py
@@ -210,7 +210,8 @@ def attn_backend_wrapper(runner: "ModelRunner", full_attn_backend: "AttentionBac
                     runner.server_args.attention_backend == "triton"
                     or runner.server_args.attention_backend == "trtllm_mha"
                     or runner.server_args.attention_backend == "fa4"
-                ), "triton or trtllm_mha or fa4 backend are the only supported backends on Blackwell GPUs for hybrid GDN models, use --attention-backend triton or --attention-backend trtllm_mha to specify the backend."
+                    or runner.server_args.attention_backend == "flashinfer"
+                ), "triton, trtllm_mha, fa4, or flashinfer backend are the only supported backends on Blackwell GPUs for hybrid GDN models, use --attention-backend to specify the backend."
             if is_npu():
                 assert (
                     runner.server_args.attention_backend == "ascend"