Generative AI Edge Processor

Sequora is a Generative AI edge processor, licensed as IP, built for combining both time-series and Generative AI workloads. Its state-space model (SSM) layers run both signal processing and neural inference on a purpose built multiply accumulate (MAC) array, to combine pre/post-processing with inference. Sequora optimizations for transformer-based-Attention and SSM operators minimize memory usage that dominates large language model (LLM) inference, enabling a complete voice-to-voice generative pipeline to run on the device without connectivity. It can support a wide range ofapplications in multiple markets including automotive, industrial IoT, defense and wearables where battery usage, latency and lack of connectivity are critical requirements. Sequora is a licensable core IP that is process-portable, fully synthesizable, verified RTL.

• ISA-Based Architecture

  Programmable like a CPU, efficient like fixed-function silicon — new algorithms ship as software.

• Unified MAC Array

  FFT- and MFCC-equivalent analysis runs on the same array as the neural layers — no DSP preprocessing stage.

• Native State-Space Processing

  SSM / R-TENNs layers hold history in a fixed-size state, so memory is constant for any signal length.

• Built for Time Series

  Audio, vibration, EEG and radar at constant compute per sample, with no frame buffering.

• Memory-Efficient Generative Decode

  Patented non-linear 4-bit codes use 4x less memory. SSM decode cuts per-token memory traffic to a level an edge platform can utilize.

• Frozen Frequency Layers

  Physics-specified values that need no retraining, so the deployed model stays certifiable.