2025-11-15 21:45:43 +08:00
|
|
|
# Design Documents
|
|
|
|
|
|
2025-11-29 04:42:39 -08:00
|
|
|
This section contains design documents and architecture specifications for vLLM-Omni.
|
2025-11-15 21:45:43 +08:00
|
|
|
|
|
|
|
|
## Architecture Documents
|
|
|
|
|
|
|
|
|
|
- [Architecture Overview](architecture_overview.md)
|
2025-12-08 16:24:16 +08:00
|
|
|
|
|
|
|
|
## Feature Design Documents
|
|
|
|
|
|
2025-12-12 01:52:53 -05:00
|
|
|
- [Disaggregated Inference](feature/disaggregated_inference.md)
|
2025-12-10 21:22:34 -05:00
|
|
|
- [Ray-based Execution](feature/ray_based_execution.md)
|
2026-08-04 14:50:38 +08:00
|
|
|
- [Async Omni Output Materialization](feature/omni_async_output_materialization.md)
|
2026-08-05 22:41:18 +08:00
|
|
|
- [Diffusion Continuous Batching](feature/diffusion_continuous_batching.md)
|
2025-12-08 16:24:16 +08:00
|
|
|
|
2026-06-01 20:20:48 +08:00
|
|
|
## Infrastructure Design Documents
|
|
|
|
|
|
|
|
|
|
- [Prometheus Metrics](metrics.md)
|
|
|
|
|
|
2025-12-08 16:24:16 +08:00
|
|
|
## Module Design Documents
|
|
|
|
|
|
2025-12-12 01:52:53 -05:00
|
|
|
- [AR Module](module/ar_module.md)
|
|
|
|
|
- [DIT Module](module/dit_module.md)
|
|
|
|
|
- [Entrypoint Module](module/entrypoint_module.md)
|