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.
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.
Other Colfax Sites
©2021 Colfax International, All rights reserved |
Terms & Conditions