// 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 LLM Decoding Engine: Temperature, Top‑k, Top‑p, and Repetition Penalty
Build a compact LLM decoding engine in Python that implements temperature, top‑k, top‑p, and repetition penalty, demonstrating real systems skill for hiring managers.
From‑Scratch int4 Weight‑Only Quantizer with Per‑Group Scales and Zero‑Points for LLM Inference
A from‑scratch int4 quantizer in pure Python, demonstrating low‑level LLM optimization skills ready for production.
Optimizing Redis Cluster Failover: Hot Key Analytics for Cache Stampede
Discover how hot key analytics can reduce cache stampede during Redis cluster failovers, with practical tuning strategies for production.
Continuous Batching LLM Serving Engine in Pure Python
A practical guide to implementing a high‑throughput LLM inference server in pure Python, complete with KV cache management and streaming output.
Build a vLLM-Style PagedAttention Inference Engine in Pure Python
Learn to implement a lightweight paged attention inference engine in Python, showcasing real systems skills for hiring managers.