Expedera’s Origin™ Evolution NPU pairs with the Cadence Tensilica NeuroEdge AICP to create a validated AI subsystem IP for higher performance, lower power, and reduced complexity in edge inference Santa Clara, California — Expedera, Inc.,…
Read More
Packet-Based NPUs In The LLM Era: From Compute-Bound CNNs To Memory-Bound Edge And Automotive Workloads
By Sharad Chole, Chief Scientist at Expedera Many Semiconductor Engineering readers know the basic story behind Expedera’s Origin NPU IP architecture: packets instead of layers, higher MAC utilization, and less gratuitous movement of activations to…
Read More
How To Start Building Edge-Native AI
Cloud AI enables features like voice assistants and recommendations via centralized data centers, but it relies on consistent network connectivity, which often fails in real-world conditions. Edge-native AI shifts inference to devices such as phones,…
Read More
Why Vision LLMs Force A Rethink Of Edge AI Hardware
As vision-centric large language models move on-device, performance measured in raw TOPS is no longer enough. Architectures need to be built around real workloads, memory behavior, and sustained utilization, especially at the edge. Vision LLMs…
Read More
Expedera’s Origin Evolution NPU IP Named Best Edge AI Processor IP in 2026 Edge AI and Vision Product of the Year Awards
Highlights Expedera’s award-winning Origin Evolution provides memory-efficient, scalable NPU IP for edge-to-data-center AI inference. Origin Evolution solves the memory and power bottlenecks that prevent real‑world deployment of GenAI at the edge. Expedera’s memory‑efficient NPUs position…
Read More




