diff --git a/python/sglang/srt/layers/flashinfer_comm_fusion.py b/python/sglang/srt/layers/flashinfer_comm_fusion.py
index a4c854bbd..9392521d4 100644
--- a/python/sglang/srt/layers/flashinfer_comm_fusion.py
+++ b/python/sglang/srt/layers/flashinfer_comm_fusion.py
@@ -204,10 +204,11 @@ if is_flashinfer_available():
 #   trtllm    | Yes   | Yes   | Yes         | Yes         | No         |
 #   mnnvl     | Yes   | Yes   | Single-node | Yes         | Blackwell  |
 #
-# FlashInfer allreduce fusion requires SM90 or SM10X. auto resolves to trtllm
-# on single-node systems and to mnnvl on Blackwell multi-node systems.
-# Non-Blackwell multi-node allreduce fusion is rejected. Explicit mnnvl remains
-# available on SM90 single-node systems.
+# FlashInfer allreduce fusion requires SM90 or SM10X. auto resolves to mnnvl
+# on Blackwell (SM100/SM103) systems (single- and multi-node) and to trtllm on
+# SM90 single-node systems. SM90 multi-node and non-SM90/SM10X configurations
+# are rejected. Either mnnvl or trtllm can be requested explicitly on
+# single-node systems, and mnnvl additionally on Blackwell multi-node.
 
 
 def is_flashinfer_allreduce_unavailable() -> bool:
diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py
index caa6967e0..01b21de03 100644
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -2122,8 +2122,8 @@ class ServerArgs:
                 "Enable FlashInfer allreduce fusion and choose backend. "
                 "Requires SM90 or SM10X NVIDIA GPUs. "
                 "Defaults to auto. "
-                "'auto': choose trtllm on single-node systems and mnnvl on "
-                "SM100/SM103 multi-node systems. "
+                "'auto': choose mnnvl on Blackwell (SM100/SM103) systems "
+                "(single- and multi-node) and trtllm on SM90 single-node systems. "
                 "'trtllm': available on single-node systems only. "
                 "'mnnvl': available on SM90 single-node systems and SM100/SM103 "
                 "single-node or multi-node systems via MNNVL fabric. "
@@ -4397,8 +4397,8 @@ class ServerArgs:
 
         # Auto-enable FlashInfer AllReduce Fusion on SM90/SM100, for models with
         # explicit support (DeepseekV3, GptOss, Glm4Moe, MistralLarge3,
-        # Qwen3/Qwen3-VL/Qwen3Next/Qwen3.5 MoE families). auto resolves to trtllm on
-        # single-node systems and mnnvl on Blackwell multi-node systems.
+        # Qwen3/Qwen3-VL/Qwen3Next/Qwen3.5 MoE families). auto resolves to mnnvl on
+        # Blackwell (single- and multi-node) and trtllm on SM90 single-node systems.
         if (
             self.flashinfer_allreduce_fusion_backend is None
             and model_arch