vllm-project/vllm-omni

[Bug]: Inaccurate x2v benchmark results

Fermée

#5 415 ouverte le 26 juil. 2026

 (3 commentaires) (0 réaction) (0 personne assignée)Python (1 067 forks)github user discovery
bughelp wantedmedium priority

Métriques du dépôt

Stars
 (4 990 étoiles)
Métriques de merge PR
 (Métriques PR en attente)

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.

Guide contributeur