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.
More from Research
- AIR: Effective-Learning-Rate Scheduler Beats Cosine on 128B-Token MoE Pretraining — stochasticchasm · 2026-10-30
- NVIDIA researcher: train robot policies with privileged sim info, improving Pi 0.5 — wellecks · 2026-10-30
- CMU's Gym-Anything Auto-Builds 200+ Agent Environments from Any Software, Selected by GDP — wellecks · 2026-10-30
- CMU Auto-Builds 25 Robot Simulations with Agents; Frontier Model Solves 0 of 25 Test Tasks — wellecks · 2026-10-30
- Leveraging Simulator Privileged Information: Three Methods to Improve Robot Models — wellecks · 2026-10-30
- DeepMind's f_charton shares his take on the current state of AI and mathematics in Sorbonne talk — f_charton · 2026-10-30