[MISC] Replace input token throughput with total token throughput (#8164

) Co-authored-by: Michael Goin <[email protected]>
vllm-project · Sep 4, 2024 · 77d9e51 · 77d9e51
1 parent e02ce49
commit 77d9e51
Showing 1 changed file with 5 additions and 5 deletions.
diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py
@@ -56,8 +56,8 @@ class BenchmarkMetrics:
     total_input: int
     total_output: int
     request_throughput: float
-    input_throughput: float
     output_throughput: float
+    total_token_throughput: float
     mean_ttft_ms: float
     median_ttft_ms: float
     std_ttft_ms: float
@@ -283,8 +283,8 @@ def calculate_metrics(
         total_input=total_input,
         total_output=sum(actual_output_lens),
         request_throughput=completed / dur_s,
-        input_throughput=total_input / dur_s,
         output_throughput=sum(actual_output_lens) / dur_s,
+        total_token_throughput=(total_input + sum(actual_output_lens)) / dur_s,
         mean_ttft_ms=np.mean(ttfts or 0) *
         1000,  # ttfts is empty if streaming is not supported by backend
         std_ttft_ms=np.std(ttfts or 0) * 1000,
@@ -426,19 +426,19 @@ async def benchmark(
                                  metrics.total_output))
     print("{:<40} {:<10.2f}".format("Request throughput (req/s):",
                                     metrics.request_throughput))
-    print("{:<40} {:<10.2f}".format("Input token throughput (tok/s):",
-                                    metrics.input_throughput))
     print("{:<40} {:<10.2f}".format("Output token throughput (tok/s):",
                                     metrics.output_throughput))
+    print("{:<40} {:<10.2f}".format("Total Token throughput (tok/s):",
+                                    metrics.total_token_throughput))
 
     result = {
         "duration": benchmark_duration,
         "completed": metrics.completed,
         "total_input_tokens": metrics.total_input,
         "total_output_tokens": metrics.total_output,
         "request_throughput": metrics.request_throughput,
-        "input_throughput": metrics.input_throughput,
         "output_throughput": metrics.output_throughput,
+        "total_token_throughput": metrics.total_token_throughput,
         "input_lens": [output.prompt_len for output in outputs],
         "output_lens": actual_output_lens,
         "ttfts": [output.ttft for output in outputs],