diff --git a/benchmarks/benchmark_throughput.py b/benchmarks/benchmark_throughput.py
index 67e509c1f5..1f65277e1b 100644
--- a/benchmarks/benchmark_throughput.py
+++ b/benchmarks/benchmark_throughput.py
@@ -523,6 +523,13 @@ def validate_args(args):
         raise ValueError(
             "Tokenizer must be the same as the model for MII backend.")
 
+    # --data-parallel is not supported currently.
+    # https://github.com/vllm-project/vllm/issues/16222
+    if args.data_parallel_size > 1:
+        raise ValueError(
+            "Data parallel is not supported in offline benchmark, \
+            please use benchmark serving instead")
+
 
 if __name__ == "__main__":
     parser = FlexibleArgumentParser(description="Benchmark the throughput.")