xcjs

I’ve had this issue on several Pixel devices - I most recently had this exact issue on my Pixel 6 Pro, but I think recent-ish Firefox updates resolved some of the issues.

In my case, Firefox would lockup, but I could easily switch to another app without an issue. I would have to kill the Firefox app to get it responsive again.

The Android version of the app still has the zoom/cursor offset bug when using a software keyboard from when they sunset RDP 8. That has been a severe usability bug for over three years now.

I consider it a big deal. I’m clicking “Not Now” buttons all day when I just want to use a piece of software for its main purpose. And then because it says “Not Now” I get asked again and again and again.

It depends on the model you run. Mistral, Gemma, or Phi are great for a majority of devices, even with CPU or integrated graphics inference.

We all mess up! I hope that helps - let me know if you see improvements!

I think there was a special process to get Nvidia working in WSL. Let me check… (I’m running natively on Linux, so my experience doing it with WSL is limited.)

https://docs.nvidia.com/cuda/wsl-user-guide/index.html - I’m sure you’ve followed this already, but according to this, it looks like you don’t want to install the Nvidia drivers, and only want to install the cuda-toolkit metapackage. I’d follow the instructions from that link closely.

You may also run into performance issues within WSL due to the virtual machine overhead.

Good luck! I’m definitely willing to spend a few minutes offering advice/double checking some configuration settings if things go awry again. Let me know how things go. :-)

It should be split between VRAM and regular RAM, at least if it’s a GGUF model. Maybe it’s not, and that’s what’s wrong?

Ok, so using my “older” 2070 Super, I was able to get a response from a 70B parameter model in 9-12 minutes. (Llama 3 in this case.)

I’m fairly certain that you’re using your CPU or having another issue. Would you like to try and debug your configuration together?

Unfortunately, I don’t expect it to remain free forever.

No offense intended, but are you sure it’s using your GPU? Twenty minutes is about how long my CPU-locked instance takes to run some 70B parameter models.

On my RTX 3060, I generally get responses in seconds.

Or maybe just let me focus on who I choose to follow? I’m not there for content discovery, though I know that’s why most people are.

I was reflecting on this myself the other day. For all my criticisms of Zuckerberg/Meta (which are very valid), they really didn’t have to release anything concerning LLaMA. They’re practically the only reason we have viable open source weights/models and an engine.

At some point, you lose productivity and reduced work weeks have shown increases in productivity can happen.

My go-to solution for this is the Android FolderSync app with an SFTP connection.

With UI decisions like the shortcut bar, they really don’t. I switched to another SMS app because I couldn’t stand it.

I tried to take hourly snapshots of an already-large Minecraft world using Git, but after a few years of snapshots, the repository became corrupted.

One of the issues was that regardless of any player-based changes that occurred, the spawn regions were always different as they were always loaded in memory.

Of course!

The Docker client communicates over a UNIX socket. If you mount that socket in a container with a Docker client, it can communicate with the host’s Docker instance.

It’s entirely optional.

There’s a container web UI called Portainer, but I’ve never used it. It may be what you’re looking for.

I also use a container called Watchtower to automatically update my services. Granted there’s some risk there, but I wrote a script for backup snapshots in case I need to revert, and Docker makes that easy with image tags.

There’s another container called Autoheal that will restart containers with failed healthchecks. (Not every container has a built in healthcheck, but they’re easy to add with a custom Dockerfile or a docker-compose.)