ane
Correctness-validated heterogeneous Laya runtime for Apple Silicon (MLX GPU + Apple Neural Engine)
Apple Silicon (M1–M4) power, GPU, ANE & memory-bandwidth monitor — sudoless TUI + Python API for profiling local LLM / MLX / CoreML inference
Run text embedding and reranking models on the Apple Neural Engine of Apple Silicon Macs. OpenAI-compatible server; ModernBERT, BERT, and XLM-RoBERTa.
Python runtime for the Apple Neural Engine