Nvidia's new runtime nearly triples protein-folding throughput

Nvidia detailed BioNeMo Inference Runtime (BioIR), a library that speeds up biomolecular structure-prediction models while staying in standard PyTorch. In an 8-GPU benchmark it delivered 58,500 folded residues per GPU-hour with the Boltz-2 model, a 2.9x gain over a torch-compiled baseline, and it already powered an AlphaFold Database expansion generating about 31 million candidate protein complexes.

Why it matters: Faster, cheaper protein-structure inference lowers the cost of large-scale computational biology, a key input for drug discovery. It's another example of AI infrastructure gains translating directly into scientific throughput rather than just chatbot performance.