cuEquivariance core

Use cuequivariance (import cuequivariance as cue) to describe group representations and tensor contractions. Prefer a built-in descriptor when it expresses the requested operation; construct a SegmentedTensorProduct only for a custom contraction. Core polynomials can be evaluated with NumPy on CPU. They do not create trainable framework parameters or select a GPU kernel.

Choose the workflow

• For built-in groups and dense descriptors, use the examples below.
• For a new group, read custom irreps.
• For custom contractions, CG paths, or polynomial inspection, read segmented polynomials.
• For dictionaries keyed by irrep, read the ir_dict workflow. It includes a CPU example and the boundary with JAX execution.