Dr. Loris M***

Scheduling Task graphs Memory Average vs peak memory usage Minimizing Parallel Graph Focusing Average Consumption Speculative decoding LLM inference optimization Throughput Optimization Multi-level Speculative Decoding Processor Scheduling Deadline-aware Scheduler Deadline Scheduling Task Scheduling Deadline-aware Mixed-criticality Tasks Caching Policies Large Language Models LLMs Online algorithms Competitive analysis of online algorithms Cache Management Mixture-of-experts Inference Optimization