A CPU-only AI Laboratory optimized for running local Large Language Models (LLMs) at peak speed using Intel OpenVINO and INT4 Weight Quantization. This lab runs entirely within Docker and uses volume ...

This repository contains CPU and HW accelerators modules synthesized in VHDL + stimuli as part of a Course Lab performed on an Intel's FPGA chip (Cyclone V). Develop skills in VHDL, focusing on code ...