[Roadmap]: getting ready to v0.11.0rc1 release #33
Description
This live page describes the roadmap to v0.11.0 release of vllm-omni, which is in companion with vllm v0.11.0. We also list help wanted item as 🙋in areas that the committer group is seeking more dedicated contributions.
Core
- Support streaming multiple requests @tzhouam [Feature] Multi Request Stream for Sync Mode #51
- Support online inference @Gaohan123 [Feature] Support online inference #64
- Refractor to vLLM v0.11.0, & dependency and requirements @Gaohan123 [Refractor] Dependency refractored to vLLM v0.11.0 #48
- Fully disaggregated architecture & key data format abstraction @natureofnature [WIP] OmniConnector for Multimodal Full Disaggregation #79
- Engine abstraction for different diffusion backend e.g., diffusers @SamitHuang [Diffusion] Qwen image support #82
Frontend
- Gradio frontend for omni model inference [Feature] Add Gradio Demo for Qwen2.5Omni #60
Model Support
- Qwen2.5-omni [Model] Add end2end example and documentation for qwen2.5-omni #14
- Qwen3-omni, @R2-Y [Feature] add support for Qwen3-omni #55
- 🙋Qwen3-Image @ZJY0516 [Diffusion] Qwen image support #82
Hardware support
- NPU backend support [Feat] Add NPU Backend support for vLLM-Omni #89
CI/CD
- CI workflow @congw729 CI Workflows. #50
- UT/ST standard following the vllm repo
Documentation
- Home
- User guide
- Developer guide
- API reference
- Community
Proposed Change.
each assignee will be responsible for open a new issue to provide detailed changes
Feedback Period.
No response
CC List.
@youkaichao @ywang96 @Isotr0py @Gaohan123 @natureofnature @fengwewn @R2-Y @tzhouam
Any Other Things.
No response
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
Sub-issues
Metadata
Metadata
Assignees
Labels
No labels