KyleandClaude Opus 5
43644de268
A pipeline materializes every component before the first stage runs, so peak memory is the sum of all components even though no two are needed at the same moment. The CPU offload flags cannot help with this: they act after loading, and on a unified-memory device moving weights to the host frees nothing because it is the same pool. Add lazy_module_load, off by default. Heavy components become a LazyModule proxy that loads on first use, and the pipeline installs a release hook on the last stage that holds each one. Peak becomes the largest overlapping set instead of the sum. Measured on MiniMax-H3 r16, 121 GiB GB10, 1 GPU, 192x320, 4 steps. Peak CUDA allocated is 57.7 GiB, reached during conditioning where the text encoder and video VAE overlap. The four deferred components account for 96.3 GiB together, which is what stays resident without the flag: text encoder 48.0, DiT 37.8, video VAE 9.7, audio VAE 0.8. Generation completed and wrote a video. Details worth flagging: The release hook lives on PipelineStage.__call__, not in the pipeline stage loop, so pipelines that override forward still free. The proxy forwards __class__, so isinstance stays honest. A proxy answering False to isinstance(module, FSDPModule) would take the wrong branch silently. Self-returning methods hand back the proxy rather than the component. Stages write self.vae = self.vae.to(device) in a dozen places; returning the component there would replace the proxy with a reference the pipeline cannot release, and the run would look normal while freeing nothing. Releasing is a latency cost, never a correctness one: a released component reloads on next access. Training keeps everything resident and warns if the flag is set. If no stage holds a deferred component the pipeline warns rather than silently doing nothing. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
FastVideo Documentation
This directory contains the FastVideo documentation built with MkDocs.
Build the docs locally
# Install dependencies
uv pip install -r requirements-mkdocs.txt
# Serve docs with live reload (recommended for development)
mkdocs serve
# Or build static site
mkdocs build
View the docs
Development server (with live reload)
mkdocs serve
Then open your browser to: http://127.0.0.1:8000
Static build
mkdocs build
python -m http.server -d site/
Then open your browser to: http://localhost:8000
Automatic Deployment
Documentation is automatically built and deployed to GitHub Pages when changes are pushed to the main branch via the .github/workflows/infra-docs.yml workflow.
Update documentation dependencies
Edit requirements-mkdocs.in, then regenerate the pinned Linux/Python 3.12 lock file:
uv pip compile requirements-mkdocs.in \
-o requirements-mkdocs.txt \
--python-platform x86_64-manylinux_2_28 \
--python-version 3.12