[MoE] Make DeepEP auto serve flashinfer_cutedsl FP4 (coerce to low_latency) + guard (#29523)

python/sglang/srt/server_args.py

@@ -6359,6 +6359,22 @@ class ServerArgs:
             )
 
         if a2a_backend == "deepep":
+            if self.moe_runner_backend == "flashinfer_cutedsl":
+                if self.deepep_mode == "auto":
+                    self.deepep_mode = "low_latency"
+                    logger.warning(
+                        "Forcing --deepep-mode low_latency: flashinfer_cutedsl "
+                        "FP4 MoE has no DeepEP normal-dispatch handler, so "
+                        "deepep auto mode would crash during prefill. "
+                        "low_latency covers both prefill and decode."
+                    )
+                elif self.deepep_mode == "normal":
+                    raise ValueError(
+                        "flashinfer_cutedsl FP4 MoE only supports DeepEP "
+                        "low_latency dispatch (masked layout). DeepEP normal "
+                        "(prefill) dispatch has no CuteDSL FP4 handler. Pass "
+                        "--deepep-mode low_latency or auto."
+                    )
             if self.deepep_mode == "normal":
                 logger.warning("Cuda graph is disabled because deepep_mode=`normal`")
                 self.cuda_graph_config.decode.backend = Backend.DISABLED