• 2 Posts
  • 2 Comments
Joined 2Y ago
cake
Cake day: Jun 12, 2023

help-circle
rss

Yes that’s a good comment for an FAQ cause I get it a lot and it’s a very good question haha. The reason I use it is for image size, the base nvidia devel image is needed for a lot of compilation during python package installation and is huge, so instead I use conda, transfer it to the nvidia-runtime image which is… also pretty big, but it saves several GB of space so it’s a worthwhile hack :)

but yes avoiding CUDA messes on my bare machine is definitely my biggest motivation


lollms-webui is the jankiest of the images, but that one’s newish to the scene and I’m working with the dev a bit to get it nicer (main current problem is the requirement for CLI prompts which he’ll be removing) Koboldcpp and text-gen are in a good place though, happy with how those are running


For people self hosting LLMs… I have a couple docker images I maintain
https://github.com/noneabove1182/text-generation-webui-docker (updated to 1.3.1 and has a fix for gqa to run llama2 70B) https://github.com/noneabove1182/lollms-webui-docker (v3.0.0) https://github.com/noneabove1182/koboldcpp-docker (updated to 1.36) All should include up to date instructions, if you find any issues please ping me immediately so I can take a look or open an issue :)
fedilink

Saw this posted over here: https://sh.itjust.works/post/163355 sounds like a really fun concept that should be shared here too :D
fedilink