diff --git a/vllm/model_executor/model_loader/loader.py b/vllm/model_executor/model_loader/loader.py
index b7b5b5e7695f4..e20da0e15fb93 100644
--- a/vllm/model_executor/model_loader/loader.py
+++ b/vllm/model_executor/model_loader/loader.py
@@ -386,7 +386,7 @@ class ShardedStateLoader(BaseModelLoader):
     Model loader that directly loads each worker's model state dict, which
     enables a fast load path for large tensor-parallel models where each worker
     only needs to read its own shard rather than the entire checkpoint. See
-    `examples/save_sharded_states.py` for creating a sharded checkpoint.
+    `examples/save_sharded_state.py` for creating a sharded checkpoint.
     """
 
     DEFAULT_PATTERN = "model-rank-{rank}-part-{part}.safetensors"