Worked on the llm-d/llm-d repository to enhance deployment flexibility and reliability for AI model inference serving. Introduced SGLang as a configurable deployment option within the inference-scheduling path, enabling modular experimentation and production workflows. The implementation involved updating YAML configuration files, refining routing logic, and leveraging environment variables to streamline deployment settings. Comprehensive Markdown documentation was added to guide users through the SGLang deployment process, improving onboarding and maintainability. The work focused on DevOps practices and Kubernetes integration, with attention to review feedback for clarity and correctness. No bugs were fixed during this period, with efforts concentrated on new feature delivery.