NVIDIA DGX SuperPOD Cuts Drug Discovery from Years to a Week
nvidia · x · 2026-08-29
Texas A&M University deployed VISION, an NVIDIA DGX SuperPOD with nearly 760 Hopper GPUs, ranking as the most powerful academic supercomputer on the June 2026 Top500 list. The system reduced drug screening time from years to a week, identifying over 22,000 candidates in a single week (compared to 120 in prior efforts) and boosting validation hit rates from 1%-10% to 80%-90%. The system maintains 95%-98% utilization and saved an estimated $1M on a single project compared to rented cloud technology.
More from Infra
- MiniMax optimizes prompt expansion latency to under 1.5s — isidentical · 2026-08-29
- Databricks Launches GLM 5.3 with Agent Routing via Unity Gateway — pwendell · 2026-08-29
- Zhipu GLM 5.3 and Flash Now Available on Ollama Cloud — ollama · 2026-08-29
- Agentic Kernel Framework Cuts Qwen-Image Latency by 42.3% — baseten · 2026-08-29
- From Scratch: Building B200 Attention Kernel to 94.4% of FA4 with 60 Diagrams — JosephJacks_ · 2026-08-29
- Gemini CLI fixes SSRF vulnerability with enhanced DNS validation and SNI preservation — diegogodinezr · 2026-08-29