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>
Configuration Options
This section lists the most common options for running vLLM-Omni.
For options within a vLLM Engine, please refer to the vLLM 0.30 configuration guide.
Each model defines fixed topology in a registered PipelineConfig and runtime
overrides in a deploy YAML.
For process-level settings shared by the CLI, deploy YAML, workers, and model integrations, see Environment Variables.
For a specific example, see the Qwen2.5-Omni deploy config. The matching frozen pipeline topology lives at vllm_omni/model_executor/models/qwen2_5_omni/pipeline.py.
For an introduction, see Pipeline and deploy configurations.
Memory Configuration
- GPU Memory Calculation and Configuration - Guide on how to calculate memory requirements and set up
gpu_memory_utilizationfor optimal performance
Optimization Features
- Diffusion Features Overview - Complete overview of all diffusion model features and supported models