• 0 Posts
  • 223 Comments
Joined 3 years ago
cake
Cake day: June 12th, 2023

help-circle

  • Yes, but some do things better than others.

    Ehhhhhh, kinda. “better” is highly subjective. Distros are “bundles of software” and a philosophy about how things are installed / when they are installed / what their default settings are / etc.

    A lot of people, especially newbs and less technical folks, grossly misunderstand what those differences are and what they mean.

    CachyOS is btrfs by default, and does btrfs better than most.

    Bullshit. Not that it’s btrfs by default but that it does it “better” than anyone else is ridiculous. It uses the same kernel driver and user-land tools as my Pop_OS install which is based on Ubuntu 24.04 and which, believe it or not, is running btrfs just fine.

    Btrfs is a bit more complex than your vanilla ext4

    Kid - I remember when ext4 was released. Very exciting to have a journaling filesystem at the time…

    Bazzite excels at gaming related things. Alpine at lightweight stuff, Nix at inmutability, etc…

    “excels” at meaning “has steam installed by default” and “makes nvidia drivers easier to install” you mean.

    My Pop_OS laptop runs game just fine.

    All these distros with their various design goals and bundled packages are variations on a theme. Like different Lego sets that include parts from a common box. But when you use the “btrfs” block you use the same one everyone else does.

    And none of them will deal gracefully with a failing disk that the OS has been told not to ignore errors on.




  • I hate when people here complain of “bloat” since often it just means “there’s this one thing I don’t use and it irrationally offends me by its existence”.

    You can uninstall just about anything you don’t want. So very much not like Windows in that regard.

    Are you running out of space? Out of memory? Or simply offended that some functionality you don’t like exists?




  • So - I setup that model according to the docs and gave it this prompt:

    Write me a highly optimized n-queens solver in go. It should take advantage of parallelism (what little there is) and output only the solution and how long it took.
    

    After 10 minutes it gave me code that didn’t compile.

    It took another 3 mins to fix the compile error and the output is not correct.

    As I said - LLMs on 8Gig VRAM just aren’t worth it.


  • It just doesn’t seem logical to me to lock me out of the whole system because a non-essential part is not working/present.

    It’s a fair criticism - but the system doesn’t know they are non-critical. You’ve, effectively, told it they are critical in fact.

    You can add a nofail option to the drives that aren’t needed to boot in /etc/fstab.

    e.g.

    UUID=9d1f7f1b-2a78-4b92-a8d5-0b05e7273920 /mnt/backup  btrfs   defaults,nofail,subvol=@backups 0 0
    

    I use this for a disk that’s external and sometimes not connected.






  • Yeah - I’ve been playing around more with the Qwen3-Coder-30B-A3B-Instruct MoE model and it’s still quite… Meh. I’ve been using llama.cpp and I’ve tried a bunch of tuning. It works and performs well enough (15t/s) but the output is just garbage. I can do some simple coding but I’m finding I’m fighting with it more than if I just wrote the code myself. Maybe I just have standards that are too high. Claude Opus 3.7 is just in an entirely different league…




  • atzanteol@sh.itjust.workstoSelfhosted@lemmy.worldDo you host your own AI?
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    2
    ·
    10 days ago

    I’ll check that out - speed isn’t my biggest issue so much as coding performance… The qwen 3.5 model I was using can write code, but it’s… Meh? Like sometimes it doesn’t even compile.

    I did try tweaking llama.cpp to do some cpu offloading and it does seem to allow for much larger contexts at a modest performance loss. I’ll check out larger models.