PyTorch

A neural network diagram showing low-rank weight matrices

From Scratch: Building a LoRA Fine-Tuning Adapter in Pure PyTorch

Implement a Low-Rank Adaptation (LoRA) module from scratch in PyTorch, then extend it with persistence, observability, and distributed training for production readiness.

A schematic of multiple LoRA adapters connected to a shared base model.

Multi-Adapter LoRA Inference Engine with Weight Paging and Shared Base

A hands‑on guide to building a multi‑adapter LoRA inference engine with weight paging and a shared base model, perfect for showcasing systems engineering skills.

Short description of the cover image subject.

Hands‑On LoRA/PEFT Portfolio Project: From Scratch to Production‑Ready Fine‑Tuning

A practical, end‑to‑end guide to building a LoRA‑based CV project from scratch, with runnable code, testing, and production‑ready extensions.

Abstract visualization of attention matrices being compressed via low-rank projection

Building a Memory-Efficient Attention with Kernel Decomposition: A Hands-On Linformer Project

Implement Linformer attention from scratch in PyTorch, benchmark it, and learn how to extend it for production systems.

Building a Sliding Window Attention Block from Scratch: A Portfolio Project for Systems Engineers

Implement a sliding‑window attention block in PyTorch, test it, and extend it with distributed training, mixed precision, and monitoring to showcase systems expertise.