[Misc] Consistent case for `vllm bench serve` results (#30403)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>

benchmarks/benchmark_serving_structured_output.py

@@ -574,7 +574,7 @@ async def benchmark(
     )
     print(
         "{:<40} {:<10.2f}".format(
-            "Total Token throughput (tok/s):", metrics.total_token_throughput
+            "Total token throughput (tok/s):", metrics.total_token_throughput
         )
     )
 

docs/benchmarking/cli.md

@@ -84,7 +84,7 @@ Total input tokens:                      1369
 Total generated tokens:                  2212
 Request throughput (req/s):              1.73
 Output token throughput (tok/s):         382.89
-Total Token throughput (tok/s):          619.85
+Total token throughput (tok/s):          619.85
 ---------------Time to First Token----------------
 Mean TTFT (ms):                          71.54
 Median TTFT (ms):                        73.88

vllm/benchmarks/serve.py

@@ -788,7 +788,7 @@ async def benchmark(
         )
     print(
         "{:<40} {:<10.2f}".format(
-            "Total Token throughput (tok/s):", metrics.total_token_throughput
+            "Total token throughput (tok/s):", metrics.total_token_throughput
         )
     )