NVIDIA open-sources BioNeMo Inference Runtime for fast, memory-efficient structure prediction
AllThingsApx · x · 2026-09-10
NVIDIA released BioNeMo Inference Runtime as a public beta, open-sourcing the acceleration behind its NIM microservices for structure prediction. The library offers GPU-accelerated inference for protein, nucleic-acid, and ligand structure prediction models.
- The team used it to generate protein structures at million-scale for the AlphaFold Database, saving substantial compute, time, and cost
- The repo includes a C++ backend, Docker, examples, and tests, supporting FASTA/MSA input through structure output
- Available on GitHub and PyPI with docs and a technical blog
More from Infra
- Grid queues make power architecture an AI-factory decision; Exowatt and Redwood offer fixes — ingliguori · 2026-10-27
- Two CVSS 9.9 Wasmtime flaws allow sandbox escape, one ARM64-only since 2020 — basedjensen · 2026-10-27
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- NVIDIA reportedly stops taking RTX 5090 orders from board partners, even backorders — chemist_slime · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27