Skip to content

vLLM-Omni

model_loader

Initializing search

vllm-project/vllm-omni

Home
User Guide
Developer Guide
API Reference
CLI Reference
Community

vLLM-Omni

vllm-project/vllm-omni

Home
User Guide
Developer Guide
API Reference
API Reference
- vllm_omni
  vllm_omni
  - data_entry_keys
  - errors
  - logger
  - outputs
  - patch
  - request
  - version
  - attention
  - config
  - core
  - diffusion
    
    diffusion
    
    compile
    
    config
    
    data
    
    diffusion_engine
    
    envs
    
    forward_context
    
    inline_stage_diffusion_client
    
    io_support
    
    ipc
    
    model_metadata
    
    output_formatter
    
    registry
    
    request
    
    stage_diffusion_client
    
    stage_diffusion_proc
    
    attention
    
    cache
    
    distributed
    
    executor
    
    hooks
    
    layers
    
    lora
    
    model_loader
    
    model_loader
    
    diffusers_loader
    
    hub_prefetch
    
    checkpoint_adapters
    
    models
    
    offloader
    
    postprocess
    
    profiler
    
    sched
    
    utils
    
    worker
  - distributed
  - engine
  - entrypoints
  - inputs
  - lora
  - metrics
  - model_executor
  - model_extras
  - platforms
  - plugins
  - profiler
  - reasoning
  - sample
  - tokenizers
  - transformers_utils
  - utils
  - worker
CLI Reference
Community

vllm_omni.diffusion.model_loader ¶

Modules:

Name	Description
`checkpoint_adapters`
`diffusers_loader`
`hub_prefetch`	Best-effort HuggingFace Hub prefetch for multi-subfolder pipelines.

Copyright © 2026 vLLM-Omni Team

Made with Material for MkDocs