// 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.

A sleek notebook with code snippets and a diagram of expert networks.

Build a Mixture-of-Experts Routing Layer from Scratch with NumPy

Implement a functional MoE routing layer in NumPy from scratch. Showcase the code on your CV to signal systems‑level engineering expertise.

A diagram of a block-based KV cache and paged attention mechanism

Build a continuous batching LLM inference engine with paged attention and block-based KV cache in pure Python

A hands-on guide to implementing a continuous batching LLM inference engine with paged attention and block-based KV cache in pure Python.

A visualization of merge operations on a token grid.

BPE Vocabulary Compression via Optimal Merge Scheduling

Learn to build a BPE tokenizer that compresses vocabulary by scheduling merges optimally, with runnable Python code and a roadmap to production.

Hands‑On Build Guide: Group‑wise INT4 Weight‑only Quantization with Per‑channel Scales and Per‑token INT8 Dynamic Activation Scaling for LLM Inference

A step‑by‑step guide to implementing group‑wise INT4 weight quantization and per‑token INT8 activation scaling from scratch in pure Python, ready for LLM inference.

A schematic of a transformer with low‑rank adapter matrices

Pure‑Python LoRA Adapter: A Portfolio Project for Systems Engineers

A hands‑on guide to implementing a pure‑Python LoRA adapter and fine‑tuning pipeline, ideal for building a portfolio project that signals real systems expertise.

Feedback