Topos Bio teams with NVIDIA cuPotential to boost molecular dynamics throughput up to 3.6x
AllThingsApx · x · 2026-11-17
Drug discovery startup Topos Bio details its collaboration with NVIDIA: running cuPotential on L4 GPUs inside OpenMM workflows lifts molecular dynamics throughput by 2.4–3.6x, and up to 7x with in-house optimizations.
The extra MD trajectories help train its generative AI models of protein motion, providing more physics-based data alongside lab experiments to uncover therapeutic opportunities.
More from Infra
- Power Is a Red Herring for AI: Frontier Compute Efficiency Grows 10x+ Per Year — teortaxesTex · 2026-11-17
- Local LLM Speed Benchmarks on RTX 4080+3080: Qwen Flash-Next Prefills Faster on One GPU Than Two — Icaruswept · 2026-11-17
- Infrathon Benchmark Tests LLM Agents on Real-World AI Infra Optimization; Claude Opus 5.5 Leads — RulinShao · 2026-11-17
- PyTorch Day Japan 2026 set for Dec 10 in Tokyo: edge deployment and kernels — PyTorch · 2026-11-17
- New BIS rule forces restricted-region chip designers to win BIS approval, ending foundry transistor-count verification — terryyuezhuo · 2026-11-17
- Baseten hits ~2,500 tok/s on DeepSeek v4.1 Flash with Vera Rubin, 1.7x faster than GB300 — baseten · 2026-11-17