Exasol Distributed ML and HPC

Trigger when the user mentions: distributed ML, machine learning, train model, batch inference, prediction, feature engineering, hyperparameter, PyTorch, TensorFlow, scikit-learn, RAPIDS, GPU model, model deployment, distributed training, ensemble, anomaly detection, forecasting, clustering at scale, k-means, gradient descent, iterative algorithm, frequent itemset, association rules, market basket, Apriori, FP-Growth, data mining, SON algorithm, partial_fit, federated training, or any pattern where data is trained or scored inside Exasol.

Routing Algorithm

Choose the narrowest matching route. Load all routes that apply — they are designed to be read together.

Route 1 — Pipeline architecture, algorithms, and patterns

Trigger phrases: distributed training, end-to-end ML, feature engineering, batch inference, ensemble, k-means, gradient descent, frequent itemset, association rules, market basket, Apriori, FP-Growth, data mining, federated training, per-entity model, anomaly detection, forecasting, hyperparameter search, map-reduce

→ Load: references/distributed-ml-patterns.md

Route 2 — Model storage, versioning, and lifecycle

Trigger phrases: save model, ONNX, joblib, pickle, model versioning, load model in UDF, update model, latest.json, model registry, model path, BucketFS model

→ Load: references/model-lifecycle.md