From Scratch Decoding: Building a Pure-Python Sampler for Transformer Logits
A hands-on guide to building a pure-Python sampler for transformer logits, covering temperature scaling, top-k, top-p, and typical-p decoding from scratch.
Systems
Build an Attention Block from Scratch: A Portfolio Project for Systems Engineers
Learn to implement a transformer attention block from scratch in Python, package it as a service, and extend it with production-grade features.
Building a Pure Python HNSW Vector Index with Disk Persistence
Learn to implement a hierarchical navigable small world graph from scratch in Python, with persistence and incremental updates, to impress hiring managers.
Building a Minimal Time-Series Database with Gorilla Compression
A hands-on guide to implementing a minimal time-series database with Gorilla compression, including architecture, code, testing, and production extensions.
Build a Pure‑Python Mixture‑of‑Experts Router from Scratch
This guide walks you through building a pure‑Python Mixture‑of‑Experts router from scratch. The result is a runnable project you can showcase on any CV.