Developer Guides#

Inference pipeline overview

The end-to-end computation flow: warmup, CUDA-graph capture, the autoregressive-step body, the ring-attention shard group, and finalize. The mental model the rest of the project assumes.

Inference pipeline overview
Config system

How every overridable field is surfaced as a CLI flag, how method defaults compose, and how to layer overrides on top.

Config system
Runner slugs and demo dispatch

How public runner names are registered, parsed, matched to manifests, and dispatched to integration-owned demo launch modes.

Application slugs and model adapter dispatch
Add a new method

The entry-point surface a new method ships against: what to subclass, what to register, and where the parity tests live.

Add a new method
Local demo benchmarks

How to run command-backed local benchmarks that capture logs, MP4s, metrics, environment metadata, and an HTML report.

Local Demo Benchmarks
flashdreams.accelerated

The low-level quantization and optimized multi-head attention building blocks used to accelerate streaming video models.

flashdreams.accelerated

Where these guides fit#

These guides are conceptual. For a specific method, see its per-model page under Models; for the per-symbol reference, see CLI and API Reference; and for the two-command path from install to a generated clip, see Get Started.