NVIDIA BioNeMo Inference Runtime enters public beta, boosting OpenFold3 over 2x on H100
AllThingsApx · x · 2026-09-11
- NVIDIA launched the BioNeMo Inference Runtime in public beta: an open, PyTorch-native library that accelerates biomolecular inference on NVIDIA GPUs.
- It speeds up structure-prediction models including Boltz-2, OpenFold2, and Protenix v2 with specialized kernels and CUDA Graphs, scaling out via Ray-powered GPU replicas.
- OpenFold3, developed by Muhammad AlQuraishi and the OpenFold Consortium, now runs >2x faster on H100 and other GPUs thanks to optimizations general-purpose compilers miss.
- Partners include apheris, Biomap, SandboxAQ, Xaira Therapeutics, and more.
More from Infra
- EdgeRock-4B holds KV cache at 72 MiB across 256K context, 99.1% smaller than Qwen3.5-4B — alifcoder · 2026-10-27
- RTX 5080 price jumps from $1658 to $2318 in ten days on Amazon — Frizzy-MacDrizzle · 2026-10-27
- ComfyUI on 12GB VRAM: measured peaks show offloading turns 24s into 11 minutes — Impossible-Mail-4619 · 2026-10-27
- Neon rebuilds its docs search entirely on its own stack: Lakebase Search, Functions, AI Gateway — matei_zaharia · 2026-10-27
- PyTorch details 2.12x faster on-device streaming ASR on Arm SME2 via ExecuTorch — PyTorch · 2026-10-27
- NVIDIA shows speculative decoding speeding up LLM inference on Jetson with Qwen3.5 9B — NVIDIA Developer · 2026-10-27