{"version":1,"type":"story","url":"https://digestai.news/story/nvidia-bioir-boosts-boltz-2-protein-folding-throughput-by-2-9x-on-h100-gpus","json":"https://digestai.news/story/nvidia-bioir-boosts-boltz-2-protein-folding-throughput-by-2-9x-on-h100-gpus.json","markdown":"https://digestai.news/story/nvidia-bioir-boosts-boltz-2-protein-folding-throughput-by-2-9x-on-h100-gpus.md","slug":"nvidia-bioir-boosts-boltz-2-protein-folding-throughput-by-2-9x-on-h100-gpus","headline":"NVIDIA BioIR boosts Boltz-2 protein folding throughput by 2.9x on H100 GPUs","summary":"NVIDIA has detailed BioNeMo Inference Runtime (BioIR), a Python library designed to accelerate biomolecular structure prediction on NVIDIA GPUs. By optimizing kernel selection, module execution via CUDA Graphs, and pipeline scaling with Ray, BioIR maintains standard PyTorch workflows while significantly improving efficiency. The tool is already deployed at scale, having powered the expansion of the AlphaFold Database by generating structures for 31 million candidate complexes across 4,777 proteomes.\n\nIn a matched benchmark using 8x H100 GPUs, BioIR-accelerated Boltz-2 achieved 58,500 folded residues per GPU-hour, compared to 20,200 for a standard torch-compiled implementation. This represents a 2.90x increase in throughput and eliminated out-of-memory errors encountered in the baseline run. NVIDIA estimates that scaling this performance to one million targets could reduce energy consumption from 35 MWh to 11 MWh, offering substantial savings for large-scale proteome campaigns.\n\nBioIR is available as an open-source GitHub repository, requiring Python 3.12+ and compatible NVIDIA drivers. It supports models like Boltz-2, OpenFold2, and OpenFold3, allowing developers to integrate optimized modules directly into custom code or use the end-to-end processor for full pipeline automation.","keyPoints":["BioIR achieves 2.90x higher throughput for Boltz-2 on 8xH100 GPUs compared to standard PyTorch implementations.","The runtime processed 31 million candidate complexes for the AlphaFold Database expansion, releasing 1.81 million high-confidence predictions.","NVIDIA estimates BioIR reduces energy usage for one million targets from 35 MWh to 11 MWh, significantly lowering computational costs."],"whyItMatters":"By drastically reducing the time and energy required for proteome-scale structure prediction, BioIR lowers the barrier for large-scale biological research. This efficiency gain enables faster drug discovery and scientific analysis, making advanced AI-driven biology more accessible and sustainable for institutions and enterprises.","category":{"slug":"hardware","name":"Hardware & Compute","url":"https://digestai.news/category/hardware"},"entities":{"companies":["NVIDIA"],"models":["Boltz-2","OpenFold2","OpenFold3"],"people":[]},"firstPublishedAt":"2026-09-10T21:57:06Z","updatedAt":"2026-09-10T21:57:06Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH100","url":"https://marktechpost.com/2026/09/10/nvidia-details-bionemo-inference-runtime-bioir-2-90x-higher-boltz-2-folding-throughput-and-58-5k-residues-per-gpu-hour-on-8xh100","publishedAt":"2026-09-10T21:57:06Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"AI Boosts Biomolecular Modeling Speed","url":"https://digestai.news/thread/nvidia-bioir-boosts-boltz-2-protein-folding-throughput-by-2-9x-on-h100-gpus","storyCount":2},"cite":{"text":"Digest AI, \"NVIDIA BioIR boosts Boltz-2 protein folding throughput by 2.9x on H100 GPUs\", 10 September 2026, https://digestai.news/story/nvidia-bioir-boosts-boltz-2-protein-folding-throughput-by-2-9x-on-h100-gpus","publisher":"Digest AI","title":"NVIDIA BioIR boosts Boltz-2 protein folding throughput by 2.9x on H100 GPUs","datePublished":"2026-09-10T21:57:06Z","url":"https://digestai.news/story/nvidia-bioir-boosts-boltz-2-protein-folding-throughput-by-2-9x-on-h100-gpus"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}