Machine-Learning

Sliding-window attention KV cache concept

Building a Sliding-Window Attention KV Cache with Dynamic Token Pruning

This guide walks through implementing a sliding-window attention KV cache with dynamic token pruning, providing runnable Python code and tests.

Python code and matrix multiplication diagrams on a dark terminal screen.

Build a FlashAttention-2 Inference Kernel from Scratch in Pure Python

Learn how to build a FlashAttention-2 inference kernel from scratch in pure Python. This guide covers tiled block-sparse causal attention and fused softmax to signal deep systems engineering skills.

A diagram of a transformer with LoRA adapters

Building a Pure-Python LoRA Adapter for BERT: A Portfolio Project

This post walks through building a LoRA adapter injection layer for BERT in pure Python, including a complete fine-tuning loop, and shows how to extend it for production-grade systems.

A visualization of speculative decoding: a fast draft model generates candidate tokens, which a larger verification model accepts or rejects in parallel.

Build a Speculative Decoding Inference Engine: A Hands-On CV Project

A hands-on build guide for a speculative decoding inference engine that uses a cheap n-gram draft model paired with a verification transformer. Includes real runnable code, architecture diagrams, and a roadmap for extending it into a production-grade system.

A visual representation of a neural network weight matrix being compressed into INT4 format.

From Scratch: Building a GPTQ INT4 Quantizer in Pure Python

Learn how to build a GPTQ INT4 quantizer from scratch in pure Python, demonstrating deep systems and ML engineering skills that stand out to hiring managers.