// 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.
From-Scratch LoRA Fine-Tuning Library in Pure NumPy
A hands‑on guide to implementing a complete LoRA fine‑tuning library in pure NumPy, complete with training, merging, and DoRA adapters.
From‑Scratch PagedAttention KV‑Cache Engine in Pure Python + NumPy
A hands‑on guide to building a production‑style KV‑cache engine from scratch, demonstrating paging, CoW sharing, and batched decode – perfect for CV signals.
Build a Pure‑Python Mixture‑of‑Experts Router from Scratch
A hands‑on guide to implementing a Mixture‑of‑Experts router from scratch in pure Python, with top‑k sparse routing and load‑balancing, ready to run and extend.
From‑Scratch GGUF & Safetensors Weight Loader in Pure Python
A from‑scratch Python loader for GGUF and safetensors weights using zero‑mmap reads, endianness/dtype conversion, tensor remapping and checksum verification.
Build a From-Scratch LLM Serving Scheduler with Chunked Prefill, Prefix Caching, and Preemption
Learn to build a lightweight LLM scheduler that demonstrates real systems skills, from architecture to production extensions.