vllm-omni

[Bugfix][CI] Enhance get_open_port function to handle port binding more robustly (#3216)

[Quantization] Enable FP8 online quantization for Z-image text encoder (#1338)

[Bugfix]pass TP size to diffusion config (#2867)

[MUSA] Add get_device_capability/get_device_version and remove get_diffusion_model_impl_qualname/prepare_diffusion_op_runtime in musa/platform.py (#3179)

[Bugfix][CI] Vendor Qwen3-TTS and CosyVoice3 reference audio fixtures (#3267)