补充 bench_serving.py里tpot等指标

python/sglang/bench_serving.py

@@ -839,10 +839,12 @@ class BenchmarkMetrics:
     mean_ttft_ms: float
     median_ttft_ms: float
     std_ttft_ms: float
+    p95_ttft_ms: float
     p99_ttft_ms: float
     mean_tpot_ms: float
     median_tpot_ms: float
     std_tpot_ms: float
+    p95_tpot_ms: float
     p99_tpot_ms: float
     mean_itl_ms: float
     median_itl_ms: float
@@ -1665,10 +1667,12 @@ def calculate_metrics(
         * 1000,  # ttfts is empty if streaming is not supported by backend
         median_ttft_ms=np.median(ttfts or 0) * 1000,
         std_ttft_ms=np.std(ttfts or 0) * 1000,
+        p95_ttft_ms=np.percentile(ttfts or 0, 95) * 1000,
         p99_ttft_ms=np.percentile(ttfts or 0, 99) * 1000,
         mean_tpot_ms=np.mean(tpots or 0) * 1000,
         median_tpot_ms=np.median(tpots or 0) * 1000,
         std_tpot_ms=np.std(tpots or 0) * 1000,
+        p95_tpot_ms=np.percentile(tpots or 0, 95) * 1000,
         p99_tpot_ms=np.percentile(tpots or 0, 99) * 1000,
         mean_itl_ms=np.mean(itls or 0) * 1000,
         median_itl_ms=np.median(itls or 0) * 1000,
@@ -1974,6 +1978,12 @@ async def benchmark(
     print("{:<40} {:<10.2f}".format("Mean TTFT (ms):", metrics.mean_ttft_ms))
     print("{:<40} {:<10.2f}".format("Median TTFT (ms):", metrics.median_ttft_ms))
     print("{:<40} {:<10.2f}".format("P99 TTFT (ms):", metrics.p99_ttft_ms))
+    print("{:<40} {:<10.2f}".format("P95 TTFT (ms):", metrics.p95_ttft_ms))
+    print("{s:{c}^{n}}".format(s="Time per Output Token (excl. 1st token)", n=50, c="-"))
+    print("{:<40} {:<10.2f}".format("Mean TPOT (ms):", metrics.mean_tpot_ms))
+    print("{:<40} {:<10.2f}".format("Median TPOT (ms):", metrics.median_tpot_ms))
+    print("{:<40} {:<10.2f}".format("P99 TPOT (ms):", metrics.p99_tpot_ms))
+    print("{:<40} {:<10.2f}".format("P95 TPOT (ms):", metrics.p95_tpot_ms))
     print("{s:{c}^{n}}".format(s="Inter-Token Latency", n=50, c="-"))
     print("{:<40} {:<10.2f}".format("Mean ITL (ms):", metrics.mean_itl_ms))
     print("{:<40} {:<10.2f}".format("Median ITL (ms):", metrics.median_itl_ms))