Worked on the foundation-model-stack/bamba repository to enhance onboarding and adoption of FP8 model quantization by developing comprehensive documentation. Focused on creating a detailed README section that explains the FP8 quantization workflow, the update included actionable code examples, a memory usage table, and a direct link to the fms-model-optimizer repository. The documentation, written in Markdown, also provided a size comparison to help users evaluate memory and performance trade-offs. By clarifying quantization steps and expected outcomes, the work improved accessibility for users planning to implement FP8 quantization, leveraging strong skills in technical writing and documentation best practices.