diff --git a/docs/.nav.yml b/docs/.nav.yml index aa6470699..e8281148b 100644 --- a/docs/.nav.yml +++ b/docs/.nav.yml @@ -32,7 +32,13 @@ nav: - design/index.md - design/architecture_overview.md - design/vllm_omni_design.md - - design/mrs_design.md + - Feature Design: + - design/feature/multi_request_streaming_design.md + - design/feature/omni_connector_design.md + - Module Design: + - design/module/ar_module_design.md + - design/module/dit_module_design.md + - design/module/entrypoint_module_design.md - Docs Guide: contributing/DOCS_GUIDE.md - API Reference: - api/README.md diff --git a/docs/README.md b/docs/README.md index 7e39ef13a..ad7a70dbf 100644 --- a/docs/README.md +++ b/docs/README.md @@ -59,4 +59,5 @@ vLLM-Omni seamlessly supports most popular open-source models on HuggingFace, in - Multi-modality generation models (e.g. Qwen-Image) For more information, checkout the following: +- [vllm-omni architecture design and recent roadmaps](https://docs.google.com/presentation/d/1Y7t2Zm3BIISPN-_X_sDpxZMNCWir2rAx/edit?usp=drive_link&ouid=110473603432222024453&rtpof=true&sd=true) - [vllm-omni announcement blogpost](https://blog.vllm.ai/2025/11/30/vllm-omni.html) diff --git a/docs/design/mrs_design.md b/docs/design/feature/multi_request_streaming_design.md similarity index 100% rename from docs/design/mrs_design.md rename to docs/design/feature/multi_request_streaming_design.md diff --git a/docs/design/feature/omni_connector_design.md b/docs/design/feature/omni_connector_design.md new file mode 100644 index 000000000..bf895c387 --- /dev/null +++ b/docs/design/feature/omni_connector_design.md @@ -0,0 +1 @@ +## OmniConnector for fully disaggregated serving (update soon) diff --git a/docs/design/index.md b/docs/design/index.md index d0393f2a7..69ae1b3ce 100644 --- a/docs/design/index.md +++ b/docs/design/index.md @@ -6,4 +6,14 @@ This section contains design documents and architecture specifications for vLLM- - [Architecture Overview](architecture_overview.md) - [vLLM-Omni Software Design Document](vllm_omni_design.md) -- [Multi-Request Streaming](mrs_design.md) + +## Feature Design Documents + +- [Multi-Request Streaming](feature/multi_request_streaming_design.md) +- [Omni Connector Design](feature/omni_connector_design.md) + +## Module Design Documents + +- [AR Module Design](module/ar_module_design.md) +- [DIT Module Design](module/dit_module_design.md) +- [Entrypoint Module Design](module/entrypoint_module_design.md) diff --git a/docs/design/module/ar_module_design.md b/docs/design/module/ar_module_design.md new file mode 100644 index 000000000..3952e94dd --- /dev/null +++ b/docs/design/module/ar_module_design.md @@ -0,0 +1 @@ +Architecture design of the AR module (update soon) diff --git a/docs/design/module/dit_module_design.md b/docs/design/module/dit_module_design.md new file mode 100644 index 000000000..e22b7d3df --- /dev/null +++ b/docs/design/module/dit_module_design.md @@ -0,0 +1 @@ +Architecture design of the DiT module (update soon) diff --git a/docs/design/module/entrypoint_module_design.md b/docs/design/module/entrypoint_module_design.md new file mode 100644 index 000000000..7a26fbb7f --- /dev/null +++ b/docs/design/module/entrypoint_module_design.md @@ -0,0 +1 @@ +Architecture design of the entrypoint (update soon)