🧠 LLM(GPT-2) Inference in C A simple and efficient C-based inference engine. [this repo is only for educational purposes] ✅ Implemented Single-threaded inference Key-Value (KV) cache for fast decoding GPT-2 model support only (converted via convert.py) ⚙️ Setup & Build Instructions (via make) 🛠️ 1. Install System Dependencies make setup 🛠️ 2. Download the model and convert it make download_gpt2 🛠️ 2. Build the Project make compile 🛠️ 3. Run the Project make run