Welcome to my blog!
I'm finally getting myself to start publishing some of the notes, ideas, and writeups that usually just sit buried somewhere in my drive. Here, I'll be writing about my research, work, and interests across deep learning, foundation models, and AI more broadly. The posts might be a bit chaotic and messy but I hope they're still useful or interesting. I really appreciate your patience (and feedback!) as I get better at sharing my thoughts more openly.
LLM Optimization Notes: Memory, Compute & Inference Techniques
These are my job preparation notes on optimizing the training and inference of large language models. This covers a range of techniques to improve memory usage, computational efficiency, and inference optimization techniques along with advanced parallelism strategies used in LLMs.