vllm-project/vllm-omni

[Bug]: Inaccurate x2v benchmark results

Open

#5,415 opened on Jul 26, 2026

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (1,067 forks)github user discovery
bughelp wantedmedium priority

Repository metrics

Stars
 (4,990 stars)
PR merge metrics
 (PR metrics pending)

Description

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.

Contributor guide

Research direction
Examine the diffusion benchmark serving.py script to find where the guidance scale parameter is missing and add it to the benchmark configuration.
Tech stack
python
Domain
testing qabackend
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65