Published
NVIDIA BioNeMo Inference Runtime (BioIR)
Accelerates biomolecular structure prediction inference for models like OpenFold3 and Boltz-2 on NVIDIA H100 and H200 GPUs.
By optimizing discovery-scale workloads, BioIR reduces the energy required to generate 31 million protein complex predictions for the AlphaFold Database by an estimated 1.35 GWh - the equivalent of 18,000 EV charges or 5.4 million electric vehicle miles.
GitHub - https://nvda.ws/3UKXFy4
Tech blog - https://nvda.ws/4dchK6H
Accelerates biomolecular structure prediction inference for models like OpenFold3 and Boltz-2 on NVIDIA H100 and H200 GPUs.
By optimizing discovery-scale workloads, BioIR reduces the energy required to generate 31 million protein complex predictions for the AlphaFold Database by an estimated 1.35 GWh - the equivalent of 18,000 EV charges or 5.4 million electric vehicle miles.
GitHub - https://nvda.ws/3UKXFy4
Tech blog - https://nvda.ws/4dchK6H
Sign in or sign up to post comments.
Be the first to comment
Up Next
-
39:00
What's new in Android Runtime (Google I/O '18)
-
01:16
NVIDIA BioNeMo Protein Binder Design Blueprint
-
27:34
Cloud Platform Live: runtime: yours
-
29:43
The Applied Science of Runtime Performance - Chrome Dev Summit 2014 (Paul Lewis)
-
04:17
Inference at Scale: The New Frontier for AI Infrastructure and ROI
-
02:27
Protecting Implicit Intents with Runtime Checks (Android Development Patterns Ep 1)
-
02:20
One Dev Question with Larry Osterman - What parts of COM are in the Windows Runtime?
-
45:07
Google I/O 2014 - The ART runtime
-
07:20
Demo: Unleashing Gemma in production with Hugging Face Text Generation Inference (TGI)
-
00:37
BioNeMo Agent Toolkit
-
01:52
NVIDIA Breakthroughs in AI Inference
-
01:23
NVIDIA Triton Inference Server: Generative Chemical Structures
-
01:59
Scaling AI Inference Performance in the Cloud with Nebius
-
36:37
Understanding Android Runtime (ART) for Faster Apps (Google I/O'19)
-
37:00
Deep Dive into the ART Runtime (Android Dev Summit '18)
-
02:24
Accelerate AI-Powered Drug Discovery With NVIDIA BioNeMo
-
01:32
NVIDIA Announces New AI Inference Platform
-
00:42
"The inflection point for inference has arrived."
-
04:21
Super Mario Bros. Movie Runtime and The Future of Nintendo IPs - IGN The Fix: Entertainment
-
12:21
Demo: Optimizing Gemma inference on NVIDIA GPUs with TensorRT-LLM
-
01:52
Inference with NVIDIA GPUs and TensorRT
-
02:15
Conversational AI Inference at Data Center Scale
Loading...