During March 2025, this developer contributed to the Furion-cn/sglang repository by implementing speculative token mapping for the EAGLE worker, focusing on enhancing speculative decoding performance and reliability. They refactored token map loading into a dedicated function, improving code maintainability and clarity. To ensure correctness, they developed comprehensive tests verifying token map usage during generation, which strengthened the robustness of the feature. Their work leveraged Python and PyTorch, applying model optimization techniques and rigorous testing practices. Although the contribution spanned a single feature over one month, it demonstrated depth in both technical execution and attention to performance and code quality.