melfie

I ran Konstakang LineageOS on a RPi4 a few years ago, but the hardware decoding didn’t work well. It might work better now. I will probably use Bigscreen once it’s available in an immutable or LTS distro, but for now, I’m using Pegasus frontend on a Linux mini PC. It’s clunky, but kind of gets the job done. Jellyfin desktop and VacuumTube work ok, but I mainly use it for games anyway. I really want Linux HTPCs to be worthy of a daily driver, and Bigscreen is the best hope as you said.

I have nearly the same setup, except OpenCode for the harness. I run 200k context for anything that doesn’t need vision, or 150k otherwise. Typically get about 30 t/s decode, starts at close to 800 t/s for prefill and drops to the 200s for a long context. I’d imagine huger decode speeds are possible with some tinkering, but I haven’t gotten around to it.

Mealie isn’t bad, but the UI makes it a huge pain to enter recipes. Luckily, the web import often works well, but some websites don’t support the JSON recipe format it requires. I recently setup llama.cpp on my server for the “AI import” feature that closes the gap well enough.

I’m assuming a lot of its training data is synthetic and distilled from Chinese models that were themselves trained from pirated data and distilled from American models trained on pirated data. It would be quite remarkable if the training data involved no piracy whatsoever. Then again, it’s open source, so I suppose it would be essentially reversing a reverse Robin Hood.

Does it support PostgreSQL now?

I used to run Gitea and switched to Forgejo mainly because I prefer a community project over one run by a for-profit company. I never had any substantive complaints against Gitea during my time with it to be honest, but thought I’d get off of it before investing too much further in case it went in a bad direction.

Self-hosted Forgejo works well for my own use. My employer is moving to GitHub Enterprise where it’s a separate instance per company with certain infra shared. Should be a slight improvement, I guess, though probably not a bad idea to make sure internal tooling is built with the git forge being configurable. 😉