// 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 server rack with glowing GPU indicators representing high-throughput LLM inference

Mastering vLLM's PagedAttention: Continuous Batching for High-Throughput LLM Inference

vLLM’s PagedAttention treats KV cache like virtual memory pages, eliminating fragmentation and enabling continuous batching that dramatically improves LLM inference throughput.

November 17, 2026 · 11 min · 2234 words · martinuke0
Python code on a notebook with MoE diagrams

Build a Pure‑Python Mixture‑of‑Experts Router with Dynamic Load‑Aware Routing and Soft Capacity Sharing

Implement a dynamic MoE router in pure Python, demonstrating load‑balancing, soft capacity sharing, and production‑ready patterns for a standout CV project.

November 17, 2026 · 8 min · 1632 words · martinuke0
Diagram of block‑tiled FlashAttention kernel

Build a From‑Scratch FlashAttention in Pure NumPy

Implement block‑tiled Q/K/V matmuls with online softmax in pure NumPy, matching naive attention while using O(N) memory; benchmark speed and memory.

November 17, 2026 · 7 min · 1471 words · martinuke0
Switch transformer router project cover

Build a Switch Transformer Router with Top‑k Gating and Auxiliary Load‑Balancing in Pure Python

Learn how to implement a switch transformer router with top‑k gating, expert capacity, and auxiliary load‑balancing loss in pure Python, and why this project signals real systems skill to hiring managers.

November 17, 2026 · 9 min · 1809 words · martinuke0
Diagram of a sliding‑window prompt manager

Dynamic Prompt‑Window Manager with Sliding‑Window Context Caching

Learn how to construct a sliding‑window context cache with importance‑based eviction, a portable project that showcases systems engineering skill for LLM‑focused roles.

November 16, 2026 · 8 min · 1641 words · martinuke0
Feedback