vLLM Quickstart: High-Performance LLM Serving
Fast LLM inference with OpenAI API
vLLM is a high-throughput, memory-efficient inference and serving engine for Large Language Models (LLMs) developed by UC Berkeley’s Sky Computing Lab.
Fast LLM inference with OpenAI API
vLLM is a high-throughput, memory-efficient inference and serving engine for Large Language Models (LLMs) developed by UC Berkeley’s Sky Computing Lab.
Real AUD pricing from Aussie retailers now
The NVIDIA DGX Spark (GB10 Grace Blackwell) is now available in Australia at major PC retailers with local stock. If you’ve been following the global DGX Spark pricing and availability, you’ll be interested to know that Australian pricing ranges from $6,249 to $7,999 AUD depending on storage configuration and retailer.
Quicknotes on printing custom planner inserts at home
Creating custom planner inserts combines the satisfaction of analog planning with the flexibility of digital design tools. Here are just the notes on printing them.
Master PDF text extraction with Python
PDFMiner.six is a powerful Python library for extracting text, metadata, and layout information from PDF documents.
Master browser automation for testing & scraping
Playwright is a powerful, modern browser automation framework that revolutionizes web scraping and end-to-end testing.
Short description and my results
This post is just to show a nice photo of the snake-arranged coals in my BBQ, ready to fire.
Technical guide to AI-generated content detection
The proliferation of AI-generated content has created a new challenge: distinguishing genuine human writing from “AI slop” - low-quality, mass-produced synthetic text.
Testing Cognee with local LLMs - real results
Cognee is a Python framework for building knowledge graphs from documents using LLMs. But does it work with self-hosted models?
Type-safe LLM outputs with BAML and Instructor
When working with Large Language Models in production, getting structured, type-safe outputs is critical. Two popular frameworks - BAML and Instructor - take different approaches to solving this problem.
Thoughts on LLMs for self-hosted Cognee
Choosing the Best LLM for Cognee demands balancing graph-building quality, hallucination rates, and hardware constraints. Cognee excels with larger, low-hallucination models (32B+) via Ollama but mid-size options work for lighter setups.
How-to with step-by-step instructions
You install KVM on Ubuntu 24.04 by checking CPU virtualization support, installing the KVM/libvirt packages, enabling the libvirtd service, and (optionally) installing virt‑manager for a GUI.
Organize Go projects efficiently with modern workspaces
Managing Go projects effectively requires understanding how workspaces organize code, dependencies, and build environments.
Bash prompt customization for instant Git context
A well-configured bash prompt displaying git repository information can dramatically improve your development workflow.
Boost SEO with breadcrumb schema and structured data
Breadcrumb navigation combined with proper schema markup is one of the most effective yet underutilized SEO techniques that can significantly improve your website’s search visibility and user experience.
Choosing between Snap and Flatpak for Linux apps
Universal package managers have transformed Linux software distribution, making cross-distribution compatibility a reality. Snap and Flatpak emerged as the leading solutions, each bringing distinct philosophies to solving dependency hell and distribution fragmentation.
Structure your Go projects for scalability and clarity
Structuring a Go project effectively is fundamental to long-term maintainability, team collaboration, and scalability. Unlike frameworks that enforce rigid directory layouts, Go embraces flexibility—but with that freedom comes the responsibility to choose patterns that serve your project’s specific needs.