diff --git a/distributed/tensor_parallelism/fsdp_tp_example.py b/distributed/tensor_parallelism/fsdp_tp_example.py
index dbab48c1b8..15052780c5 100644
--- a/distributed/tensor_parallelism/fsdp_tp_example.py
+++ b/distributed/tensor_parallelism/fsdp_tp_example.py
@@ -87,7 +87,7 @@
 dp_mesh = device_mesh["dp"]
 
 # For TP, input needs to be same across all TP ranks.
-# while for SP, input can be different across all ranks.
+# while for DP, input can be different across all ranks.
 # We will use dp_rank for setting the random seed
 # to mimic the behavior of the dataloader.
 dp_rank = dp_mesh.get_local_rank()