How project reporting became a performance — and what it takes to build a dashboard that actually drives decisions on a capital project.Continue reading on Medium »
I benchmarked three implementations, and learned something useful about why long-context speculative decoding is actually slower…Continue reading on Medium »
A guide to the Vespa Cloud metrics dashboard — how to move from symptom to bottleneck to action, and what’s new in the latest revision.
I have tested how OpenCode works with several locally hosted on Ollama and llama.cpp LLMs, and for comparison, added some Free models from OpenCode Zen.OpenCode is one of the most promising tools in the AI developer tools ecosystem right now.TL;DR — Op…
The industry stopped asking, ‘What’s possible?’ and started asking, ‘Who can deliver?’
Posted by Alan Kelly, Software Engineer
One of our previous articles, Optimizing TensorFlow Lite Runtime Memory, discusses how TFLite’s memory arena minimizes memory usage by sharing buffers between tensors. This means we can run models on eve…