Neural network weights and code editor representing QLoRA fine‑tuning.

Hands-On Build Guide: QLoRA Fine‑Tuner From Scratch in PyTorch with NF4 Quantization and LoRA Merging

A step‑by‑step guide to training a quantized LLaMA‑style model with QLoRA, merging LoRA adapters, and packaging the result as a portable CV asset.

September 11, 2026 · 7 min · 1333 words · martinuke0
Python code editor with cache manager diagram

Pure‑Python Paged Attention KV‑Cache Manager: LRU & Random Eviction

Build a lightweight, pure‑Python KV‑cache manager that implements LRU and random eviction strategies, complete with paging, testing, and extension pathways for senior‑level topics.

September 11, 2026 · 9 min · 1903 words · martinuke0

Hands-On Build Guide: Pure‑Python GGUF Weight Loader with Lazy Memory‑Mapped Tensor Initialization

A step‑by‑step guide to creating a pure‑Python GGUF weight loader that lazily memory‑maps tensors, perfect for demonstrating low‑level Python systems skills on a CV.

September 10, 2026 · 2 min · 232 words · martinuke0
LoRA adapter illustration

Build a LoRA Adapter Layer from Scratch in PyTorch

A hands‑on guide to building a LoRA adapter layer in pure PyTorch, with complete code, merge/unmerge, and tips for turning the project into a CV‑standing side project.

September 10, 2026 · 7 min · 1439 words · martinuke0
A sleek laptop screen displaying a terminal with model benchmark output.

Hands-On Build Guide: Quantization‑Aware Portfolio Project for Engineering CV

A step‑by‑step guide to creating a quantization‑aware tool that you can ship, benchmark, and showcase in job interviews.

September 9, 2026 · 8 min · 1515 words · martinuke0
Feedback