915 B
915 B
Design Documents
This section contains design documents and architecture specifications for vLLM-Omni.
Architecture Documents
Feature Design Documents
- Disaggregated Inference
- Ray-based Execution
- Async Omni Output Materialization
- Adding Step Execution Support for Diffusion Pipelines
- Request-Level Batching for Diffusion
- Continuous Batching for Step-Wise Diffusion