Aashay Kulkarni

About

I am a student of Systems Engineering and Computer Science at the University of Illinois Urbana-Champaign. I am interested in the confluence of Systems and AI, particularly in leveraging parallel computing across distributed systems to train large language models (LLMs). To pursue this interest, I am currently studying CUDA to write efficient systems-level code and utilize the parallel computing power of GPUs.

Projects

• MNIST-CUDA: MNIST trained neural network written from scratch in C++ and CUDA with both CPU and GPU implementations.
• GPT-2: Recreated GPT-2 from Scratch (Coming Soon)
• AIAYN: Reproduced the Attention is All You Need Paper from Scratch (Coming Soon)

Certifications

• Machine Learning Specialization
• Advanced Learning Algorithms
• Unsupervised Learning & Reinforcement Learning

Notes

• cuda-notes: in progress notes taken from "Programming Massively Parallel Processors"

“And once the storm is over, you won’t remember how you made it through, how you managed to survive. You won’t even be sure, whether the storm is really over. But one thing is certain. When you come out of the storm, you won’t be the same person who walked in. That’s what this storm’s all about.”

- Haruki Murakami