NVIDIA BioNeMo Inference Runtime enters public beta to speed biomolecular inference

AllThingsApx · x · 2026-09-10

NVIDIA launched the public beta of BioNeMo Inference Runtime, an open, PyTorch-native library that accelerates biomolecular structure prediction on NVIDIA GPUs with specialized kernels and CUDA Graphs. It supports models like Boltz-2, OpenFold2 and Protenix v2, and scales with Ray-powered GPU replicas, with collaborators including SandboxAQ, Xaira Therapeutics and Latent Labs.

Related event: NVIDIA Open-Sources BioNeMo Inference Runtime in Public Beta(9 posts)→

Original post →

More from Infra

Infra channel →