Posts
All the articles I've posted.
Serving ML Models in Production with FastAPI + ONNX
Published: at 10:00 AMLearn how to serve machine learning models in production using FastAPI and ONNX Runtime. Export a Hugging Face NLP model to ONNX, build a REST inference endpoint, benchmark performance against native PyTorch, and containerize the service with Docker.
Semantic Segmentation of Point Clouds with PointNet++
Published: at 12:30 PMA practical guide to semantic segmentation of 3D point clouds with PointNet++. Learn why point clouds are hard for neural networks, how PointNet++ builds a hierarchical feature representation with sampling and grouping, and how to implement the key building blocks in PyTorch, with a worked example on the S3DIS indoor dataset.
Fine-tuning LLMs with LoRA: A Practical Guide
Published: at 10:00 AMA practical guide to fine-tuning Large Language Models with LoRA (Low-Rank Adaptation). Learn how parameter-efficient fine-tuning works, why it dramatically reduces compute and memory, and how to implement it end-to-end using Hugging Face PEFT and Transformers, including QLoRA for consumer GPUs.