1. “Dissecting GPU Utilization for LLM Inference on Nvidia Hopper“, Mohammad Siavashi, Gerald Q. Maguire Jr., Dejan Kostić, and Marco Chiesa, Proceedings of the IEEE International Symposium on Workload Characterization (IISWC), September 2026. To appear.
  2. “Queue-Mem: Energy-Efficient Hardware Storage for Advanced Network Function Acceleration“, Mariano Scazzariello, Tommaso Caiazzi, Hamid Ghasemirahni, Dejan Kostić, and Marco Chiesa, Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation (NSDI), May 2026.
  3. “KVComm: Enabling Efficient LLM Communication through Selective KV Sharing“, Xiangyu Shi, Marco Chiesa, Gerald Q. Maguire Jr., and Dejan Kostic, Proceedings of the Fourteenth International Conference on Learning Representation (ICLR). April 2026.
  4. “Cloud abstractions for AI workloads“, Marco Canini, Theophilus A. Benson, Ricardo Bianchini, Íñigo Goiri, Dejan Kostić, Peter Pietzuch, Simon Peter, Proceedings of the 16th ACM SIGOPS Asia-Pacific Workshop on Systems (ApSys), October 2025.
  5. “Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning“, Laura Puccioni, Alireza Farshin, Mariano Scazzariello, Changjie Wang, Marco Chiesa, and Dejan Kostić, Proceedings of the Second International Workshop on Large Language Models for Code (LLM4Code), May 2025.
  6. “Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues“, Daniele Cipollone, Changjie Wang, Mariano Scazzariello, Simone Ferlin, Maliheh Izadi, Dejan Kostić, and Marco Chiesa, Proceedings of the Second International Workshop on Large Language Models for Code (LLM4Code), May 2025.
  7. “Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference“, Mohammad Siavashi, Faezeh Keshmiri Dindarloo, Dejan Kostić, and Marco Chiesa, Proceedings of the 5th Workshop on Machine Learning and Systems (EuroMLSys), March 2025.