GitHub · Python
InferMatrixLab/vllm-omni-mlx
High-performance OpenAI and Anthropic compatible omni-modality model inference server for Apple Silicon.
- Stars
- 27
- Forks
- 4
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: asr, diffusion-models, inference-engine, omni-modal, tts, vllm, vllm-omni
Latest data point: Nov 21, 2026 · 27 stars · 4 forks