[benchmark] add max-concurrency in result table (#21095)

Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>

benchmarks/benchmark_serving.py

@@ -413,6 +413,10 @@ async def benchmark(
 
     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))

benchmarks/benchmark_serving_structured_output.py

@@ -555,6 +555,10 @@ async def benchmark(
 
     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))

vllm/benchmarks/serve.py

@@ -486,6 +486,12 @@ async def benchmark(
 
     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))