xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 06:35:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Minor Fix] Fix comments in benchmark_serving (#3252)

Browse Source
This commit is contained in:
TianYu GUO 2024-03-08 14:22:59 +08:00 committed by GitHub
parent c59e120c55
commit 1ece1ae829
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
benchmarks/benchmark_serving.py
View File

@ -12,7 +12,7 @@ On the server side, run one of the following commands:
On the client side, run: On the client side, run:
python benchmarks/benchmark_serving.py \ python benchmarks/benchmark_serving.py \
--backend <backend> \ --backend <backend> \
--tokenizer <your_model> --dataset <target_dataset> \ --model <your_model> --dataset <target_dataset> \
--request-rate <request_rate> --request-rate <request_rate>
""" """
import argparse import argparse
@ -171,10 +171,10 @@ async def benchmark(
else: else:
raise ValueError(f"Unknown backend: {backend}") raise ValueError(f"Unknown backend: {backend}")
pbar = None if disable_tqdm else tqdm(total=len(input_requests))
print(f"Traffic request rate: {request_rate}") print(f"Traffic request rate: {request_rate}")
pbar = None if disable_tqdm else tqdm(total=len(input_requests))
benchmark_start_time = time.perf_counter() benchmark_start_time = time.perf_counter()
tasks = [] tasks = []
async for request in get_request(input_requests, request_rate): async for request in get_request(input_requests, request_rate):