biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Fix some issues with benchmark data output (#13641)

Browse Source 
Signed-off-by: Huy Do <huydhn@gmail.com>
This commit is contained in:
Huy Do
2025-02-23 18:23:18 -08:00
committed by GitHub
parent cbae7af552
commit e7ef74e26e
7 changed files with 61 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
benchmarks/benchmark_latency.py
View File

@@ -11,7 +11,7 @@ from typing import Any, Dict, List, Optional
import numpy as np
import torch
from benchmark_utils import convert_to_pytorch_benchmark_format
from benchmark_utils import convert_to_pytorch_benchmark_format, write_to_json
from tqdm import tqdm
from vllm import LLM, SamplingParams
@@ -30,8 +30,7 @@ def save_to_pytorch_benchmark_format(args: argparse.Namespace,
for k in ["avg_latency", "percentiles"]})
if pt_records:
pt_file = f"{os.path.splitext(args.output_json)[0]}.pytorch.json"
with open(pt_file, "w") as f:
json.dump(pt_records, f)
write_to_json(pt_file, pt_records)
def main(args: argparse.Namespace):