VisionNet v1.0 is a configurable CNN accelerator IP designed to deliver efficient edge inference for vision workloads.
- NPU
We specialize in designing and developing advanced IP cores for AI accelerators, optimizing AI inference at the edge with low-power, high-performance solutions. By providing researchers and industries with state-of-the-art IP, we empower them to drive innovation, accelerate development, and address complex challenges with highly efficient AI technology.
VisionNet v1.0 is a configurable CNN accelerator IP designed to deliver efficient edge inference for vision workloads.
Configurable transformer accelerator
For fast, low-power edge AI inference on Stories260K, Stories15M, SmolLM 135M, LLaMA 3.2, and custom models, supporting FP32, INT8, and INT4.