Daniel J Walsh

Yes to use vllm currently you need to pull a specific --image to make it work. We are working on making ramalama pick the correct vllm image. BTW vllm will...

I do not believe any progress has been made on this.

I would prefer these all to be based off a base image with all of the python tools required to run ramalama and then rocm, vulcan, ... can all share...

Yes all images should be available in as many arches as makes sense.

@slp @ericcurtin we need to get this in, so we can run on Mac with Containers.

@pufferffish this might interest you.

Please sign all of your commits.

@bmahabirbu PTAL

@ericcurtin PTAL @Tojaj Please take into account the changes suggesed by AI Surgery. @Tojaj I like where this is going. Might be worth breaking apart this PR into multiple different...

We have moved to ramalama chat, which has some rag support. Closing this since it seems like it is not being worked on. Reopen if you are making progress.