SolidRun and Gyrfalcon Develop First Edge Optimized AI Inference Server That Bests GPU Performance at a Fraction of the Cost and Power

SolidRun and Gyrfalcon Technology introduced a co-developed Arm®-based AI inference server optimized for the edge (SRGT-AI31). Highly scalable and modular, Janux GS31 supports today’s leading neural network frameworks and can be configured with up to 128 Gyrfalcon Lightspeeur SPR2803 AI acceleration chips for unrivalled inference performance for today’s most complex video AI models.