SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐
AI-native tensor format (.ptt) for protein-structure ML. Convert a structure or sequence once; load backbone, MSA, ESM embeddings, sparse pair features, and ligands with zero parsing. Feeds AlphaFold/Boltz (Boltz-2 verified). Zarr-backed, lossless, PyTorch/JAX-ready, streams from S3/GCS.