anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Doc] Fix mkdocs. (#785)

Browse Source 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
This commit is contained in:
Alicia authored and GitHub committed 2026-01-15 10:38:27 +08:00
1 parent 1fe64e85a6
commit 314bb4e324
5 files changed
+13 -23
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/design/architecture_overview.md
+8 -8
View File
@@ -64,13 +64,13 @@ According to analysis for current popular open-source models, most of them have
## Key Components
| Component | Description |
|-----------|-------------|
| **OmniRouter** | provide an intelligent router for Omni-modality requests dispatch |
| **EntryPoints** | define the APIs for offline/online serving (APIServer, Omni/AsyncOmni) and provide the OmniStage abstraction for different AR/DiT stages |
| **AR** | adapted for omni-modality models while inheriting efficient features from vLLM, such as cache management |
| **Diffusion** | natively implemented and optimized using acceleration components |
| **OmniConnector** | supports fully disaggregation based on E/P/D/G (Encoding/Processing/Decoding/Generation) disaggregation across stages |
| Component | Description |
| ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| **OmniRouter** | provide an intelligent router for Omni-modality requests dispatch |
| **EntryPoints** | define the APIs for offline/online serving (APIServer, Omni/AsyncOmni) and provide the OmniStage abstraction for different AR/DiT stages |
| **AR** | adapted for omni-modality models while inheriting efficient features from vLLM, such as cache management |
| **Diffusion** | natively implemented and optimized using acceleration components |
| **OmniConnector** | supports fully disaggregation based on E/P/D/G (Encoding/Processing/Decoding/Generation) disaggregation across stages |
Disaggregated stages are managed through configuration, such as in the Qwen3-Omni example, where stages like Thinker, Talker, and Code2wav are defined as separate OmniStage instances with specific resources and input/output type.
@@ -192,4 +192,4 @@ curl -sS -X POST http://localhost:8091/v1/chat/completions \
}
```
For more usages, please refer to [examples](../user_guide/examples/).
For more usages, please refer to [examples](../examples/README.md).