| Domain Rule | Design Constraint | Rust Implication |
| Large data | Efficient memory | Zero-copy, streaming | | GPU acceleration | CUDA/Metal support | candle, tch-rs | | Model portability | Standard formats | ONNX | | Batch processing | Throughput over latency | Batched inference | | Numerical precision | Float handling | ndarray, careful f32/f64 |
| Inference only | tract (ONNX) | Lightweight, portable | | Training + inference | candle, burn | Pure Rust, GPU | | PyTorch models | tch-rs | Direct bindings | | Data pipelines | polars | Fast, lazy eval |
Da utilizzare durante la creazione di app ML/AI in Rust. Parole chiave: machine learning, ML, AI, tensore, modello, inferenza, rete neurale, deep learning, training, previsione, ndarray, tch-rs, brucia, candela, 机器学习, 人工智能, 模型推理 Fonte: zhanghandong/rust-skills.