diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py
index f3a20842137e..bb8ee7d0a2f9 100644
--- a/benchmarks/benchmark_serving.py
+++ b/benchmarks/benchmark_serving.py
@@ -520,6 +520,10 @@ async def limited_request_func(request_func_input, pbar):
 
     print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="="))
     print("{:<40} {:<10}".format("Successful requests:", metrics.completed))
+    if max_concurrency is not None:
+        print("{:<40} {:<10}".format("Maximum request concurrency:", max_concurrency))
+    if request_rate != float("inf"):
+        print("{:<40} {:<10.2f}".format("Request rate configured (RPS):", request_rate))
     print("{:<40} {:<10.2f}".format("Benchmark duration (s):", benchmark_duration))
     print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))
     print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output))
diff --git a/benchmarks/benchmark_serving_structured_output.py b/benchmarks/benchmark_serving_structured_output.py
index e23a5a9e2233..fc5d795a431f 100644
--- a/benchmarks/benchmark_serving_structured_output.py
+++ b/benchmarks/benchmark_serving_structured_output.py
@@ -569,6 +569,10 @@ async def limited_request_func(request_func_input, pbar):
 
     print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="="))
     print("{:<40} {:<10}".format("Successful requests:", metrics.completed))
+    if max_concurrency is not None:
+        print("{:<40} {:<10}".format("Maximum request concurrency:", max_concurrency))
+    if request_rate != float("inf"):
+        print("{:<40} {:<10.2f}".format("Request rate configured (RPS):", request_rate))
     print("{:<40} {:<10.2f}".format("Benchmark duration (s):", benchmark_duration))
     print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))
     print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output))
diff --git a/vllm/benchmarks/serve.py b/vllm/benchmarks/serve.py
index 8b16fea9e3d3..8e63b7bf677c 100644
--- a/vllm/benchmarks/serve.py
+++ b/vllm/benchmarks/serve.py
@@ -477,6 +477,12 @@ async def limited_request_func(request_func_input, pbar):
 
     print("{s:{c}^{n}}".format(s=' Serving Benchmark Result ', n=50, c='='))
     print("{:<40} {:<10}".format("Successful requests:", metrics.completed))
+    if max_concurrency is not None:
+        print("{:<40} {:<10}".format("Maximum request concurrency:",
+                                     max_concurrency))
+    if request_rate != float('inf'):
+        print("{:<40} {:<10.2f}".format("Request rate configured (RPS):",
+                                        request_rate ))
     print("{:<40} {:<10.2f}".format("Benchmark duration (s):",
                                     benchmark_duration))
     print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))