Dr. Sebastian Lehrig

[FEEDSTOCK REQUEST] vllm

3

**Describe the package you'd like added** `vllm` has become a popular inference server for LLMs: https://github.com/vllm-project/vllm **Describe how this package fits in with the project** GenAI/LLMs fit to core values...

[FEEDSTOCK REQUEST] ollama

1

**Describe the package you'd like added** `ollama` has become a popular easy-to-setup environment for LLMs: https://github.com/ollama/ollama **Describe how this package fits in with the project** GenAI/LLMs fit to core values...

[FEEDSTOCK REQUEST] llama.cpp & llama-cpp-python

1

**Describe the package you'd like added** `llama.cpp` has become a popular inference server for LLMs. Additionally, `llama-cpp-python` is commonly used to connect from Python to `llama.cpp`. - `llama.cpp`: https://github.com/ggerganov/llama.cpp -...

Umbrella Issue: Porting Kubeflow to IBM Power (ppc64le)

19

/kind feature Enable builds & releases for IBM Power (ppc64le architecture). This proposal was presented [with these slides ](https://github.com/kubeflow/kubeflow/files/9862922/2022-10-25.Porting.Kubeflow.to.IBM.Power.pdf) at the [2022-10-25 Kubeflow community call](https://bit.ly/kf-meeting-notes) with positive community feedback. We...

Improve build performance via caching

3

/kind feature **Why you need this feature:** Minimizing CI build times is always good! My team estimates that enabling caching can lower building times of Kubeflow components by 30-40% on...