From 5842a74815c1338ee557195dd84592c0cbb12d5b Mon Sep 17 00:00:00 2001 From: Hongsheng Liu Date: Wed, 31 Dec 2025 13:42:11 +0800 Subject: [PATCH] [docs] update adding models docs (#563) Signed-off-by: hsliu --- docs/.nav.yml | 2 +- docs/contributing/model/README.md | 20 +++---------------- ...ti_stage_model.md => adding_omni_model.md} | 2 +- 3 files changed, 5 insertions(+), 19 deletions(-) rename docs/contributing/model/{adding_multi_stage_model.md => adding_omni_model.md} (99%) diff --git a/docs/.nav.yml b/docs/.nav.yml index 7b357de83..47adb8799 100644 --- a/docs/.nav.yml +++ b/docs/.nav.yml @@ -40,7 +40,7 @@ nav: flatten_single_child_sections: true - Model Implementation: - contributing/model/README.md - - contributing/model/adding_multi_stage_model.md + - contributing/model/adding_omni_model.md - contributing/model/adding_diffusion_model.md - CI: contributing/ci - Tests: contributing/tests diff --git a/docs/contributing/model/README.md b/docs/contributing/model/README.md index bb7f83680..b3e951c8b 100644 --- a/docs/contributing/model/README.md +++ b/docs/contributing/model/README.md @@ -4,26 +4,12 @@ This section provides comprehensive guidance on how to add a new model to vLLM-O ## Documentation -- **[Adding a New Omni Model Guide](adding_multi_stage_model.md)**: Complete step-by-step guide using Qwen3-Omni as an example +- **[Adding an Omni-Modality Model](adding_omni_model.md)**: Complete step-by-step guide using Qwen3-Omni as an example. -The guide covers: -- Directory structure and organization -- Implementing stage components (thinker, talker, code2wav) -- Creating the unified model class -- Model registration -- Stage configuration -- Stage input processors -- Testing strategies - -- **[Adding a New Diffusion Model Guide](adding_diffusion_model.md)**: Complete step-by-step guide using Qwen/Qwen-Image-Edit as an example -The guide covers: -- Overview -- Directory Structure -- Step-by-Step Implementation -- Testing +- **[Adding a Diffusion Model](adding_diffusion_model.md)**: Complete step-by-step guide using Qwen/Qwen-Image-Edit as an example. ## Quick Start -For a quick reference, see the [Adding a New Multi-Stage Model Guide](adding_multi_stage_model.md) and [Adding a New Diffusion Model Guide](adding_diffusion_model.md). +For a quick reference, see the [Adding a New Multi-Stage Model Guide](adding_omni_model.md) and [Adding a New Diffusion Model Guide](adding_diffusion_model.md). diff --git a/docs/contributing/model/adding_multi_stage_model.md b/docs/contributing/model/adding_omni_model.md similarity index 99% rename from docs/contributing/model/adding_multi_stage_model.md rename to docs/contributing/model/adding_omni_model.md index 0af2605ca..0a66c1709 100644 --- a/docs/contributing/model/adding_multi_stage_model.md +++ b/docs/contributing/model/adding_omni_model.md @@ -1,4 +1,4 @@ -# Adding a Multi-Stage Model +# Adding an Omni-Modality Model This guide walks through the process of adding a new multi-stage model to vLLM-Omni, using **Qwen3-Omni** as a comprehensive example. Qwen3-Omni is a multi-stage omni-modality model that demonstrates the full capabilities of vLLM-Omni's architecture.