InferMatrixLab /
vllm-omni-mlx
High-performance OpenAI and Anthropic compatible omni-modality model inference server for Apple Silicon.
Updated 35 min ago
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
Targets Apple Silicon Macs using MLX, with no GPU cluster needed. Serves chat and speech synthesis, and includes a Qwen3-based speech recognition endpoint.
Summary written by AI from the repository’s description and README.
InferMatrixLab / vllm-omni-mlx
View on GitHub(opens in new tab)