diff --git a/fastdeploy/config.py b/fastdeploy/config.py
index 8d9aa9ab08f..4cf05ea989f 100644
--- a/fastdeploy/config.py
+++ b/fastdeploy/config.py
@@ -1601,6 +1601,14 @@ def __init__(
         self.check()
         self.print()
 
+    def _disable_sequence_parallel_moe_if_needed(self, mode_name):
+        if self.parallel_config.use_sequence_parallel_moe and self.graph_opt_config.use_cudagraph:
+            self.parallel_config.use_sequence_parallel_moe = False
+            logger.warning(
+                f"Sequence parallel MoE does not support {mode_name} mode with cudagraph. "
+                "Setting use_sequence_parallel_moe to False."
+            )
+
     def postprocess(self):
         """
         calculate some parameters
@@ -1685,10 +1693,12 @@ def postprocess(self):
             logger.info("Multi-modal models do not support prefix caching when using CUDAGraph!")
 
         if self.scheduler_config.splitwise_role == "mixed":
+            self._disable_sequence_parallel_moe_if_needed("Mixed")
             self.model_config.moe_phase = MoEPhase(phase="prefill")
         elif self.scheduler_config.splitwise_role == "prefill":
             self.model_config.moe_phase = MoEPhase(phase="prefill")
         elif self.scheduler_config.splitwise_role == "decode":
+            self._disable_sequence_parallel_moe_if_needed("PD's decode node")
             self.model_config.moe_phase = MoEPhase(phase="decode")
         else:
             raise NotImplementedError
diff --git a/requirements.txt b/requirements.txt
index c0b762958f6..2e016837dd4 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -37,7 +37,7 @@ opentelemetry-api>=1.24.0
 opentelemetry-sdk>=1.24.0
 opentelemetry-instrumentation-redis
 opentelemetry-instrumentation-mysql
-opentelemetry-distro 
+opentelemetry-distro
 opentelemetry-exporter-otlp
 opentelemetry-instrumentation-fastapi
 opentelemetry-instrumentation-logging