GSI Technology Reports 3-Second Time-to-First-Token for Edge Multimodal LLM Inference on Gemini-II

Using the Gemma-3 12B vision-language model on GSI’s production Gemini-II processor, GSI achieved the 3-second TTFT while consuming approximately 30 watts at the AI sub-system, including the chip. To ...
Electropages

Edge AI solutions accelerated by NVIDIA Jetson Thor unveiled

Advantech has introduced a new lineup of application-focused Edge AI solutions powered by NVIDIA Jetson Thor modules. The NVIDIA Jetson Thor series set a new benchmark for edge AI, delivering up to ...
Design-Reuse

DeepTransformCore® Plus – High-Performance Multi-modal Edge LLM Accelerator (LLaMA 3.1 & Mini-Omni2)

DeepTransformCore® Plus is a high-performance Multimodal LLM AI accelerator engineered for multi-modal interactions (Text, Voice, and Image) at the ed ...
Design And Reuse

Quadric, Inference Engine for On-Device AI Chips, Raises $30M Series C as Design Wins Accelerate Across Edge

BURLINGAME, Calif. -- Quadric®, the inference engine that powers on-device AI chips, today announced an oversubscribed $30 million Series C funding round, bringing total capital raised to $72 million.