I am Sai Saketh Cherukuri, a final-year M.Sc. student in Mathematics with a specialization in Computer Science at the Sri Sathya Sai Institute of Higher Learning. My work sits at the intersection of mathematical rigor and high-performance computing, specifically in the domain of LLM inference optimization and system-level efficiency.

As an active contributor to the open-source AI ecosystem, I specialize in hardware acceleration and performance tuning using the vLLM engine. I am currently leveraging the MLPerf Inference benchmark suite to evaluate industry-standard models like Llama 3.1-8B, applying a mathematical lens to analyze the statistical significance of throughput variances across different quantization kernels.

By combining a deep understanding of mathematical modeling with practical GPU-level implementation, I aim to bridge the gap between theoretical optimization and practical systems engineering. My goal is to build scalable, cost-transparent solutions that make high-performance machine learning accessible and economically sustainable for the global developer community.