Partner

Apex Compute develops AI accelerator IP for FPGA and ASIC platforms. Our technology is optimized for transformer-based AI inference, including large language models (LLMs), vision-language models (VLMs), and vision-language-action (VLA) models for robotics and autonomous systems. The solution combines a highly efficient compute architecture with an open-source software stack that enables seamless deployment of PyTorch models on FPGA platforms while delivering industry-leading performance-per-watt for edge AI applications.