Colfax AIEdge™ servers featuring Untether AI’s tsunAImi accelerator cards helps companies running AI workloads to run neural networks faster, cooler, and cheaper using at-memory computing. The bundled imAIgine Software Development Kit (SDK) from Untether AI provides an automated path to running networks at high performance freeing data scientists from having to perform low-level optimization tasks and instead spend time where it matters to them – crafting their models.
Inquire
Download tsunAImi Product Brief
Financial Technology
Smart City
Smart Retail
Industrial Vision
AI as a Service (AIaaS)
By moving the compute element directly adjacent to memory cells, Untether AI’s groundbreaking at-memory architecture provides unrivaled compute density, accelerating AI inference for diverse neural networks such as vision, natural language processing, and recommendation engines. This technology is embodied in Untether AI’s runAI200 devices and tsunAImi accelerator cards.
Powered by 4 runAI200 devices, the tsunAImi accelerator cards provides 2 POPs of compute power. This compute power translates into over 80,000 frames per second of ResNet-50 v 1.5 throughput at batch=1. For natural language processing, tsunAImi accelerator cards can process over 12,000 queries per second (qps) of BERT-base.
imAIgine Software Development Kit (SDK) from Untether AI provides an automated path to running networks at high performance with push-button quantization, optimization, physical allocation, and multi-chip partitioning. The imAIgine SDK frees data scientists from having to perform low-level optimization tasks and instead spend time where it matters to them – crafting their models. The imAIgine SDK also provides an extensive visualization toolkit, cycle-accurate simulator, and an easily integrated runtime API.
Get your project rolling with quick answers from technical sales to address your unique challenges.
All product, brand, or trade names used on this page are the trademarks or registered trademarks of their respective owners.