Views
No views yet
safetensors for pure-Rust inference.| Model | Architecture | Input | Output | Purpose |
|---|---|---|---|---|
solver_selector | 28 → 128 → 64 → 6 | Instance features (28-D) | Solver probabilities (6 classes) | Recommend best VRP solver for an instance |
quality_predictor | 28 → 64 → 32 → 2 | Instance features (28-D) | Gap (%), tour length (km) | Predict route quality before solving |
automl | 28 → 64 → 5 | Instance features (28-D) | Max iter, temp, tabu, cooling, neighbourhood | Instance-aware hyperparameter tuning |
move_scorer | 16 → 32 → 16 → 1 | Move features (16-D) | Improvement score | Score 2-opt candidate moves for local search |
graph_embed | GraphSAGE placeholder | Node features (10-D) | 64-D embeddings | Road network node embeddings (placeholder) |
solver_selector, quality_predictor, and automl is a 28-dimensional normalized feature vector extracted from a VRP instance:n_stops, n_vehicles, avg_pairwise_km, lat_spread, lon_spread, density, area_km2, depot_centroid_distknn_avg_degree, knn_max_degree, knn_clustering, knn_diameter, knn_mst_weight, knn_avg_shortest_path, knn_spectral_gap, knn_assortativitytotal_demand, demand_std, tight_capacity_flag, capacity_ratiodist_mean, dist_std, dist_skewness, depot_dist_meanmin_distance, min_time, balance_load, min_vehiclessolver_selector predicts among:defaultclarke_wrightsweepor_opttwo_optneural_guidedstate_dict keys remapped to Candle lin{N}.weight / lin{N}.bias convention1use candle_core::Device;
2use candle_nn::{linear, Linear, Module, VarBuilder};
3
4let vb = VarBuilder::from_tensors(tensors, DType::F32, &device);
5let lin1 = linear(28, 128, vb.pp("lin1"))?;
6let lin2 = linear(128, 64, vb.pp("lin2"))?;
7let lin3 = linear(64, 6, vb.pp("lin3"))?;