NVIDIA open-sources BioNeMo Inference Runtime to speed up protein structure prediction
AllThingsApx · x · 2026-09-11
NVIDIA released the BioNeMo Inference Runtime in public beta: an open-source, PyTorch-native library that accelerates biomolecular inference on NVIDIA GPUs.
- Specialized kernels for models including Boltz-2, OpenFold2, and Protenix v2, with CUDA Graphs support where available
- Scales via Ray-powered GPU replicas
- Built with collaborators including apheris, SandboxAQ, Xaira Therapeutics, and UW's protein design lab
For protein structure prediction and bio-AI work, it means faster inference and a more open engineering stack.
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- Gary Marcus: With Q3 data added, Anthropic's compute-efficiency growth shows deceleration — GaryMarcus · 2026-10-27
- SpaceX locks in $40B GPU financing deal with Apollo, the largest ever committed — TechCrunch AI · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- vLLM eyes Rust migration as inference engines race to rewrite the stack — AccBalanced · 2026-10-27