Skip to content

Inferencing API Overview

Use the Inferencing API to implement model components, and pipelines to run inference on World Models.

Guides

Create a modelImplement and register a model integration with FlashDreams. Stream inference pipelineBuild stateful generation with streaming pipeline contracts. Profiling a pipelineMeasure pipeline stages with CUDA event or NVTX profilers. Accelerated building blocksUse optimized attention, quantization, caching, and execution components.

API Reference

Pipeline APIReference for inference pipelines and reusable infrastructure. Core APIReference for model-agnostic core components and utilities. Accelerated APIReference for optimized attention, quantization, and shared inference components.