Skill UI

Compress large language models quickly using Wanda, SparseGPT, and N:M pruning to enforce hardware-friendly sparsity, enabling faster inference and deployment without retraining.

Guides ML deployment workflows by surfacing best practices, templated code, and validation steps whenever model pruning helper patterns are mentioned.

A comprehensive guide to authoring, optimizing, and validating Power Query M expressions used within semantic model partitions. This resource covers crucial topics such as maintaining query folding for performance, applying early filtering and column pruning, and leveraging the Power Query API for robust data validation and debugging.