// 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.
Python code on a laptop screen with neural network diagrams

Hands‑On Build Guide: Speculative Decoding Inference Engine in Python

A step‑by‑step tutorial to build a speculative decoding inference engine in pure Python, demonstrating model parallelism, benchmarking, and production‑grade extensions.

September 24, 2026 · 7 min · 1482 words · martinuke0
A visual representation of the Sigstack ecosystem showing Cosign, Fulcio, and Rekor components working together in a software supply chain pipeline.

Implementing Sigstore: Modern Cryptographic Signing for Secure Software Supply Chains

Sigstore provides a free, open-source framework for signing software artifacts with short-lived certificates. This post walks through implementing Cosign, Fulcio, and Rekor to secure your supply chain and meet SLSA compliance goals.

September 24, 2026 · 8 min · 1694 words · martinuke0
A checklist icon representing title uniqueness

Title Uniqueness: How to Avoid Duplicate Headings in Hugo and Beyond

A practical guide to detecting and preventing duplicate titles in Hugo, with CI checks and metadata best practices for SEO.

September 24, 2026 · 6 min · 1208 words · martinuke0
NVIDIA Triton Inference Server dashboard showing GPU utilization and model metrics

Deep Dive into NVIDIA Triton Inference Server: Scaling Multi‑Model GPU Workloads

NVIDIA Triton Inference Server is a critical tool for scaling AI in production. This deep dive explores its architecture, multi-model concurrency, and deployment patterns.

September 24, 2026 · 7 min · 1460 words · martinuke0
Abstract representation of digital safety shields protecting user data and interactions

User Safety: Building Systems That Protect by Default

Explore how modern engineering teams bake user safety into system architecture using safe defaults, guardrail patterns, and layered defenses — from content moderation to consent flows — ensuring harm is prevented before it reaches end users.

September 24, 2026 · 10 min · 1972 words · martinuke0
Feedback