👋 Hello, welcome to my repo!

I'm Cheng Fei, a Machine Learning Engineer at AWS Annarpurna Labs, with expertise in Large Language Models (LLM), Deep Neural Networks (DNN), and High Performance Computing (HPC).

👨‍💻 Open to Roles

• Machine Learning Engineer
• Applied Scientist

🤖 Projects - Large Language Models (LLM/DNN)

• 🏭 Transformer -- a decoder-only character-level transformer for text generation

• ⛳ LLM Red Teaming -- a LLM-powered red teaming platform

• ✨ AssetGPT -- an LLM-powered financial analyst platform

• 🏙 CNN Classifier -- a CNN-driven architecture style classifier

• 🚘 DQN Route Planner -- a DQN-driven route planner

• ⚙️ MiniTorch -- a mini-version of core PyTorch modules

• 🔥 PyTorch Programming -- a collection of DNN implementations in PyTorch

😋 Projects - LLMs from Scratch

• 👽 Transformers from Scratch -- a collection of transformer models rebuilt

• 🎨 Diffusers from Scratch -- a collection of diffusion models rebuilt

• 🚀 vLLM from Scratch -- a collection of vLLM models rebuilt

🌌 Projects - High Performance Computing (HPC)

• 🎯 CUDA Programming -- a collection of CUDA kernel optimizations for GPU

• 🔱 Triton Programming -- a collection of Triton server optimizations for GPU

• 🧬 Neuron Programming -- a collection of Neuron distributed training optimizations for Trainium Accelerator

• 🔀 Parallel C++ Programming -- a collection of parallel computing optimizations in C++

📙 Blogs - SOTA LLM Researches

• 🌐 LLM Research Explained -- a detailed explanation of SOTA LLM researches and technologies

📚 Blogs - CS Cheatsheets

• 📄 SDE Cheatsheet - a collection of popular software engineering technology stacks

• 📜 AS/MLE Cheatsheet - a collection of popular applied science research or machine learning engineering technology stacks

📈 GitHub Stats