Selected Works
Guardrails
A cost-effective, low-latency prompt filtration system
Distributed Machine Learning System
Scaling Traditional Machine Learning using cuML
Multi Modal RAG
Feeding texts and images into language models
Latest Posts
Benchmarking ML APIs
Comparing FastAPI and Crow.Cpp for serving ML models.
Introduction to Guardrails
A prompt filtration system that ensures safe interactions
Benchmarking Model Serving Libraries
A quick guide to comparing model serving libraries for fast, efficient ML deployments.