Dejan Milojicic

PRR slashes decoding latency by up to 40% in long-context LLMs while maintaining accuracy, revolutionizing the efficiency of dynamic sparse attention.

Festina slashes energy consumption by up to 56% in serverless LLM serving while ensuring SLOs are met, revolutionizing energy optimization in cloud workloads.

Forget scaling compute – the future of AI hinges on a 1000x leap in energy efficiency via tight AI+Hardware co-design over the next decade.