vllm-project/vllm-omni

[Bug]: Inaccurate x2v benchmark results

已關閉

#5,415 建立於 2026年7月26日

 (3 則留言) (0 個反應) (0 位負責人)Python (1,067 個分叉)github user discovery
bughelp wantedmedium priority

倉庫指標

星標
 (4,990 顆星)
PR 合併指標
 (PR 指標待抓取)

描述

Your current environment

Your output of `python collect_env.py` here

Your code version

🐛 Describe the bug

The diffusion_benchmark_serving.py script does not enable the guidance scale parameter. The default guidance scale parameter causes the benchmark to only run positive tests during the low-noise phase, omitting negative tests, resulting in inaccurate latency measurements.

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

貢獻者指南