RNGD meets Backend.AI:
AI Inference Infrastructure for the Era of Sovereign AI
A benchmark look at RNGD on Backend.AI
Purpose-built inference accelerators are designed to handle the same serving work with less power, lowering the operating cost of always-on inference services. See how Backend.AI operates FuriosaAI's RNGD inference accelerator in a single control plane, and what matched-condition benchmarks show about throughput and power efficiency.
Related Services
Backend.AI is a vendor-agnostic accelerated workload hosting platform based on our own home-grown orchestration and job scheduler, running on top of either cloud or on-premises (air-gapped) clusters.
Explore service →FuriosaAI designs data-center AI accelerators purpose-built for inference. RNGD, built on the Tensor Contraction Processor architecture, serves large language models at high power efficiency with a 180W TDP per card.
Learn more →