Eric Curtin
Eric Curtin
@sbrivio-rh thanks, sorry for the repeated poke, I saw it again yesterday and noticed this issue was going stale... Wanted it to remain non-stale...
@amila-ku I think we have this in docker model runner if you want to contribute there: https://github.com/docker/model-runner Please star, fork and contribute!
The solution here is update the Fedora package, this is expected behaviour because the Fedora version is old (doesn't have the concept of model store enabled, it does have a...
Nack, will approve if there is a test that actually performs vllm + safetensors inferencing
I think we should merge this... But we do have a vulkan image based on kompute also... It's all about naming... Please working with @slp and @rhatdan to agree on...
@sroecker please sign your commit, this is failing the DCO build: ``` git commit --amend -s ``` to sign an old commit.
I think this image should inherit from the kompute one like @rhatdan said, if anything it makes the Containerfiles easier to maintain, less duplication. I notice this container image was...
Pretty much all images that can be x86_64/aarch64, should be. I think the ROCm one will be x86_64 only, but that's because some of the required things aren't built for...
@sroecker if we inherit FROM quay.io/ramalama/ramalama:latest stick in this directory: container-images/vulkan and rebuild llama.cpp and whisper.cpp with the options you used here. I think we can get this in now.
We implemented this in another PR