Real projects, practical insights, and a look behind the code.
Stay up to date with the latest from the Caplaz software engineering blog
Welcome to the latest updates from the Caplaz software engineering blog. Here you’ll find hands-on project breakdowns, tips from real-world development, and insights that blend thoughtful design with technical depth. Whether you’re into edge AI, mobile apps, or modern dev workflows, there’s something here to spark ideas and support your build.
-
Running llama.cpp on the Jetson Nano
So you’ve built GCC 8.5, survived the make -j6 wait, and now you’re eyeing llama.cpp like it’s your ticket to local AI greatness on a $99 dev board.With a few workarounds (read: Git checkout, compiler gymnastics, and a well-placed patch), you can run a quantized LLM locally on your Jetson Nano with CUDA 10.2, GCC 8.5, and a Prayer. Will it…
-
Compiling GCC 8.5 on Jetson Nano
Let’s be real: working with CUDA 10.2 on the Jetson Nano is like trying to install Photoshop on a potato. It can work — but only if you speak its ancient dialect. That dialect? GCC 8.x. Let’s build! Whether you’re experimenting with local LLMs, compiling CUDA-based projects, or just tired of getting slapped by “unsupported compiler” errors,…
-
Updating Python on Your Jetson Nano Like a Pro
So, you’ve dusted off your trusty Jetson Nano, a noble edge AI companion from yesteryear — and you’re ready to teach it some new tricks. There’s just one problem: it’s still rocking Python 3.6, like it’s stuck in 2018. Time to update that thing and unlock the magical powers of Python 3.8, 3.10, or even the…