Diffusers Dynamic Offloader

DDO is a model-agnostic offload manager for low-VRAM Diffusers-style inference. It provides dense-weight routes and official Diffusers compatibility routes while preserving quantized backend math.

Getting started

Follow the installation guide, then choose full-pipeline, staged or Modular Diffusers integration.

Normal linear use requires no native allocator or compiler. Native VMM is optional: it uses a matching packaged DLL/.so and bootstrap before CUDA initialization. The installation guide describes local candidate wheels; it does not assume they are available on a package index.

from diffusers_dynamic_offloader import enable_offload

result = enable_offload(transformer, preset="auto", component="transformer")
transformer = result.module

This snippet selects the default linear route. See native VMM integration for its separate loading contract.

Documentation

• User guides: installation, integration, presets and reporting.
• Developer guides: architecture, diagnostics, builds and validation.

Examples and benchmarks

Model runners, custom-block integration and measured comparisons live in DDO examples. See the test hardware and support boundaries when interpreting results. Selected workloads do not establish universal speedups or model support.

License

Apache-2.0; preserve required copyright, license and attribution notices.