xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 03:15:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
This commit is contained in:
Peter Pan 2025-07-30 16:15:43 +08:00 committed by GitHub
parent fc91da5499
commit 533db0935d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
benchmarks/benchmark_serving.py
View File

@ -413,6 +413,10 @@ async def benchmark(
print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="=")) print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="="))
print("{:<40} {:<10}".format("Successful requests:", metrics.completed)) 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} {:<10.2f}".format("Benchmark duration (s):", benchmark_duration))
print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input)) print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))
print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output)) print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output))

4
benchmarks/benchmark_serving_structured_output.py
View File

@ -555,6 +555,10 @@ async def benchmark(
print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="=")) print("{s:{c}^{n}}".format(s=" Serving Benchmark Result ", n=50, c="="))
print("{:<40} {:<10}".format("Successful requests:", metrics.completed)) 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} {:<10.2f}".format("Benchmark duration (s):", benchmark_duration))
print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input)) print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))
print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output)) print("{:<40} {:<10}".format("Total generated tokens:", metrics.total_output))

6
vllm/benchmarks/serve.py
View File

@ -486,6 +486,12 @@ async def benchmark(
print("{s:{c}^{n}}".format(s=' Serving Benchmark Result ', n=50, c='=')) print("{s:{c}^{n}}".format(s=' Serving Benchmark Result ', n=50, c='='))
print("{:<40} {:<10}".format("Successful requests:", metrics.completed)) 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):", print("{:<40} {:<10.2f}".format("Benchmark duration (s):",
benchmark_duration)) benchmark_duration))
print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input)) print("{:<40} {:<10}".format("Total input tokens:", metrics.total_input))