NVIDIA BioNeMo Inference Runtime Enters Public Beta, Speeds Protein Models Like Boltz-2 on GPUs

AllThingsApx · x · 2026-09-11

NVIDIA has released BioNeMo Inference Runtime in public beta — an open, PyTorch-native library that accelerates biomolecular inference on NVIDIA GPUs for drug discovery and protein design.

Key points:

Related event: NVIDIA Open-Sources BioNeMo Inference Runtime, Boosting Structure Prediction Throughput up to 2.9x(14 posts)→

Original post →

More from Infra

Infra channel →