NVIDIA BioNeMo Inference Runtime enters public beta, speeding protein structure prediction on GPUs

AllThingsApx · x · 2026-09-13

NVIDIA announced the public beta of BioNeMo Inference Runtime, an open, PyTorch-native library that accelerates biomolecular inference on NVIDIA GPUs. It supports optimizing models like Boltz-2, OpenFold2, and Protenix v2 with specialized kernels and CUDA Graphs, scaling via Ray-powered GPU replicas, with collaborators including apheris, SandboxAQ, and Xaira Therapeutics. The post also quotes a joke benchmarking a 166K-parameter fruit fly protein model against AlphaFold.

Original post →

More from Research

Research channel →