[⚡️Post] Learning-to-Rank Intuition feat. RAXLearning to Rank (LTR) sits at the heart of many systems we interact with daily — from search engines to recommendation systems. Let’s…Dec 11, 2024Dec 11, 2024
Token Intuition: Understanding Costs, Throughput, and Scalability in Generative AI ApplicationsTLDR; Tokens are deceivingly cheap. Real world Gen AI applications are complex. Anyone looking to deploy Gen AI applications at scale need…Dec 10, 2024Dec 10, 2024
Deploying vLLM on Google Cloud: A Guide to Scalable Open LLM InferenceLarge Language Models (LLMs) have become central to many modern applications, but deploying them efficiently at scale presents unique…Dec 2, 2024Dec 2, 2024
A Hacker’s Guide to Neural Collaborative Filtering with PyTorch LightningCollaborative Filtering (CF) has been the cornerstone of modern recommendation systems, with matrix factorization (MF) serving as the…Dec 1, 2024Dec 1, 2024
Fastai’s DataBlock APIThe DatBlock API from fast ai is a powerful part of the fastai library. I find it a beautiful and elegant solution for building data…Aug 20, 2024Aug 20, 2024