Worked on the llm-d/llm-d repository to design and document a ModelService Helm Chart Deployment Proposal, enabling reproducible and scalable deployment of large language models and LoRA adapters within Kubernetes environments. The approach centered on a declarative configuration using Helm Charts, allowing users to manage Kubernetes resources efficiently for serving both base models and adapters. The proposal detailed motivations, goals, non-goals, and integration points with the existing llm-d ecosystem, providing clear implementation guidance. The work relied on Markdown for documentation and leveraged skills in Kubernetes, Helm Charts, and LLM deployment, focusing on maintainability and ecosystem compatibility rather than direct code changes.