Jiaxin Shan

em. The most elegant way is to extend https://github.com/kubernetes/kubernetes/blob/5ab4b580de915cffd901c7a1304aca5fdcca88e7/pkg/kubelet/cm/container_manager_stub.go#L89-L91 However, this is a dependency that we can not easily bring back to kubesim. I filed an upstream PR https://github.com/kubernetes/kubernetes/pull/100267 Once...

em. currently, in-place-vpa doesn't support custom resource yet. this requires a more concrete plan and use cases and I think that's the beta item. Can we consider the alignment in...

@Barakmor1 Thanks for the details. I misunderstood the scope and I will take a look at the KEP and come back to you on the potential change

@ari9dam May I ask a question. Even the shareGPT data is `multi-turn`, when we convert it into data that could be finetuned. We still need to change it to `instruction/input/output`...

@genggui001 I found this one as well https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered

@ramyaprabhu-alt Just curious the code release would be a separate project or a PR against vLLM? I think it's a PR, right?

@robvanderleek We have a solution for EKS now. Please let us know if you are interested in it

@robvanderleek This is implemented like a device plugin in Kubernetes. I doubt it can be used in ECS directly. But overall the GPU sharing theory is similar and I think...

Let's also add some orchestration support in the roadmap. Seems how to orchestrate such stateful application is not covered yet. Let's create one sub-task to track it

@yyzxw could you try latest v0.3.0-rc.1 release instead of v0.2.1? They are not compatible. the sample linked above is latest but v0.2.1 still use legacy code