// TODO: I’m martinuke0

Welcome to my corner of the internet. This website is a personal blog which I use as a platform to document my learning journey and showcase it for the world to see.

Code editor showing a Python tokenizer implementation with token merges and a vocabulary table.

Build a WordPiece Tokenizer From Scratch: A CV-Worthy NLP Project

Build a production-shaped WordPiece tokenizer in Python with subword merging, BERT special tokens, and a greedy decode path. Includes runnable code, tests, and a roadmap to senior-level extensions.

Layered diagram of a quantization pipeline showing calibration, packing, and fused dequantize-matmul.

Build a GPTQ int4 Quantization Engine in Python/NumPy

Ship a runnable int4 weight-only quantization engine from scratch: GPTQ-style calibration, group-wise affine scales, and a fused dequantize-matmul kernel. Built to demonstrate real ML systems skill on a portfolio.

Diagram of mixed-precision AdamW with ZeRO-1 sharding across GPUs.

Building Mixed-Precision AdamW with ZeRO-1 from Scratch in Pure PyTorch

A runnable, from-scratch implementation of mixed-precision AdamW with dynamic loss scaling and ZeRO-1 sharded optimizer state in pure PyTorch — built to demonstrate real systems engineering, not just model design.

Abstract visualization of sliding attention windows over a token timeline

Building a Sliding-Window Attention Manager from Scratch

A from-scratch, runnable Python project that mimics the memory management at the heart of modern LLMs: sliding-window attention with dynamic eviction and a prefix-cache KV store. Includes architecture, code, tests, and a roadmap to senior-level.

Diagram of a mixed-precision training loop showing forward, autocast, loss scaling, and a custom CUDA bf16 kernel.

Building a Mixed-Precision GPT Trainer From Scratch: A CV-Grade ML Systems Project

A working engineer’s guide to building a from-scratch mixed-precision training loop — gradient scaling, dynamic loss scaling, and a custom bf16 tensor kernel — applied to a mini GPT. Includes architecture, runnable code, and a roadmap for turning the toy into a portfolio-grade ML systems project.

Feedback