hsliu_ustc
c88408d825
Announce the v0.30.0 release in the README news section (unified full-duplex framework, cross-stage KV/multimodal transfer, LingBot World interactive serving, MiniMax H3 Turbo on Blackwell/Ascend 950) and refresh the supported-model examples (Tencent AuK, Breeze-TTS-2, LingBot World, MAGI-2, pi0.5; drop removed dots.tts-era examples). Point the pre-built wheel and image instructions at the published 0.30.0 artifacts (PyPI wheel verified; ROCm 0.30.0/rocm723 wheel index verified), update the vLLM configuration and environment-variable references from 0.29 to 0.30, and move the NPU source-clone tag from v0.30.0rc1 to the final v0.30.0 release. Signed-off-by: hsliu_ustc <hsliu_ustc@noreply.gitcode.com>
3.2 KiB
3.2 KiB
hide
| hide | ||
|---|---|---|
|
Welcome to vLLM-Omni
Easy, fast, and cheap omni-modality model serving for everyone
<script async defer src="https://buttons.github.io/buttons.js"></script> Star Watch Fork
About
vLLM was originally designed to support large language models for text-based autoregressive generation tasks. vLLM-Omni is a framework that extends its support for omni-modality model inference and serving:
- Omni-modality: Text, image, audio, video, and action data processing
- Non-autoregressive Architectures: extend the AR support of vLLM to Diffusion Transformers (DiT) and other parallel generation models
- Heterogeneous outputs: from traditional text generation to multimodal and action outputs
vLLM-Omni is fast with:
- State-of-the-art AR support by leveraging efficient KV cache management from vLLM
- Pipelined stage execution overlapping for high throughput performance
- Fully disaggregation based on OmniConnector and dynamic resource allocation across stages
vLLM-Omni is flexible and easy to use with:
- Heterogeneous pipeline abstraction to manage complex model workflows
- Seamless integration with popular Hugging Face models
- Tensor, pipeline, data and expert parallelism support for distributed inference
- Streaming outputs
- OpenAI-compatible API server
- Full-duplex realtime serving with streaming audio input and output
vLLM-Omni seamlessly supports most popular open-source models on HuggingFace, including:
- Omni-modality models (e.g. Qwen3-Omni, MiniCPM-o 4.5, Cosmos3, HunyuanImage, BAGEL)
- TTS models (e.g. Qwen3-TTS, Tencent AuK, Breeze-TTS-2, CosyVoice3)
- Diffusion models — image, video, and audio generation (e.g. MiniMax H3, LingBot World, MAGI-2, LTX-2.5, Wan2.2)
- Robot-policy and action models (e.g. π0.5, GR00T-N1.7, DreamZero-DROID, InternVLA-A1)
For more information, checkout the following: