chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Fix] Add TPOT back to bench_serving (#12976)

Browse Source
This commit is contained in:
elvischenv
2025-11-11 17:32:24 +08:00
committed by GitHub
parent e3b38d7194
commit 71aea45c41
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
python/sglang/bench_serving.py
View File

@@ -2052,6 +2052,12 @@ 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(
"{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("{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))