feat: Adds a slim cuda docker image. - #1867
Open
MicahZoltu wants to merge 1 commit into
Open
Conversation
Unlike the others, this one clocks in at under 1GB, compared to cuda-devel which is something like 20GB. It serves the WebUI by default so users can just run it with a model and get to generating without needing to learn a CLI or build a usable wrapper.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Unlike the other docker images, this one clocks in at under 1GB, compared to cuda-devel which is something like 20GB. It serves the WebUI by default so users can just run it with a model and get to generating without needing to learn a CLI or build a usable wrapper.
Related Issue / Discussion
I did this for myself, since I didn't want a 20+GB image, and figured others may benefit so am sharing it. Feel free to close if this isn't desired and I'll just keep it in my fork.
Additional Information
Only tested with Minimax H3 so far, but it works great on my 5090!
4s video @ 384x384 takes under 90 seconds to generate (longer playtime runs out of VRAM and takes an order of magnitude longer to generate even just 5 seconds)
here-be-dragons.webm
Checklist