Python code on a laptop screen with tokenization diagrams

Reversible Byte-Level BPE Tokenizer Trainer with Streaming Merge Accumulation

A hands‑on guide to training a byte‑level BPE tokenizer from scratch, with streaming merge accumulation and byte‑exact roundtrip testing, perfect for demonstrating systems engineering skill.

September 19, 2026 · 10 min · 1993 words · martinuke0
A developer working on a laptop

Building a Production-Ready Personal CV API with Next.js and Prisma

A practical guide to building a personal CV API with Next.js and Prisma, showcasing systems engineering skills.

September 19, 2026 · 8 min · 1533 words · martinuke0
A sleek Python script running on a laptop, illustrating a router directing traffic to expert modules.

Hands‑On Build: Mixture‑of‑Experts Top‑K Gating Router in Pure Python

A step‑by‑step guide to implementing a mixture‑of‑experts router from scratch in Python, complete with top‑k gating, auxiliary loss, and production‑ready extensions.

September 17, 2026 · 9 min · 1907 words · martinuke0
NumPy code on a laptop screen illustrating attention matrices

Hands‑On Build Guide: Page‑Transformer Inference with Greedy KV‑Cache Eviction and Paged Attention in Numpy

A step‑by‑step guide to implementing a lightweight page‑transformer with paged attention and KV‑cache eviction, ready to run and extend.

September 16, 2026 · 9 min · 1721 words · martinuke0
Python code on a laptop screen next to a model file

Hands‑On Build Guide: Pure‑Python Safetensors Parser & Weight Shard Assembler with mmap Lazy Loading

A step‑by‑step guide to creating a lightweight, mmap‑based safetensors parser you can ship, test, and extend for real‑world model serving.

September 16, 2026 · 7 min · 1452 words · martinuke0
Feedback