NVIDIA launches BioNeMo Inference Runtime public beta for faster protein structure prediction
AllThingsApx · x · 2026-09-10
NVIDIA Health announced the public beta of BioNeMo Inference Runtime, an open, PyTorch-native library for faster biomolecular inference on NVIDIA GPUs.
- Optimizes structure-prediction models including Boltz-2, OpenFold2, and Protenix v2 with specialized kernels and, where supported, CUDA Graphs.
- Scales inference with Ray-powered GPU replicas.
- Backed by collaborators including apheris, Latent Labs, SandboxAQ, Xaira Therapeutics, and the Institute for Protein Design at UW.
More from Infra
- Hyperscalers could factor RSA-1024 for about $30M per number, analysis claims — rickasaurus · 2026-09-11
- Qualcomm's Next Hexagon NPU: 50% More Shared Memory, 30B MoE Models on a Phone — ryanshrout · 2026-09-11
- Vercel Cut CDN P99 Metadata Lookup Latency by 91% Across 80M Route Decisions/sec — cramforce · 2026-09-11
- OreoLook: three-layer caching for low-latency LLM web search on commodity CPUs — pollinations · 2026-09-11
- Analyst: NAND's DRAM moment — DeepSeek V4.1 Flash keeps 26% of params on SSD — casper_hansen_ · 2026-09-11
- NVIDIA BioNeMo kernels hit 7.1x speedup on triangle attention in Terray's drug discovery benchmarks — AllThingsApx · 2026-09-11