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

[CI] the readability of benchmarking and prepare for dashboard (#5571)

Browse Source 
[CI] Improve the readability of performance benchmarking results and prepare for upcoming performance dashboard (#5571)
This commit is contained in:
Kuntai Du
2024-06-17 11:41:08 -07:00
committed by GitHub
parent ab66536dbf
commit 9e4e6fe207
8 changed files with 213 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
benchmarks/benchmark_latency.py
View File

@@ -98,7 +98,7 @@ def main(args: argparse.Namespace):
for _ in tqdm(range(args.num_iters), desc="Profiling iterations"):
latencies.append(run_to_completion(profile_dir=None))
latencies = np.array(latencies)
percentages = [10, 25, 50, 75, 90]
percentages = [10, 25, 50, 75, 90, 99]
percentiles = np.percentile(latencies, percentages)
print(f'Avg latency: {np.mean(latencies)} seconds')
for percentage, percentile in zip(percentages, percentiles):