collaborators

9 papers

cs.NI2026

Avoiding Cross-Datacenter Collective Congestion via Disaggregated Buffering

Mariano Scazzariello, Noga H. Rotman, Dima Gavrilenko +6

LLM training at the scale of tens of thousands of GPUs now spans multiple datacenters (DC), making cross-DC collectives over long-haul links unavoidable. A critical and overlooked…

cs.DC2026

Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC

Mohammad Siavashi, Mariano Scazzariello, Gerald Q. Maguire +2

Large Language Model (LLM) inference is rapidly becoming a core datacenter service, yet current serving stacks keep the host CPU on the critical path for orchestration and token-le…

cs.LG2026

KVComm: Enabling Efficient LLM Communication through Selective KV Sharing

Xiangyu Shi, Marco Chiesa, Gerald Q. Maguire +1

Large Language Models (LLMs) are increasingly deployed in multi-agent systems, where effective inter-model communication is crucial. Existing communication protocols either rely on…

cs.SE2025

Dissect-and-Restore: AI-based Code Verification with Transient Refactoring

Changjie Wang, Mariano Scazzariello, Anoud Alshnakat +3

Formal verification is increasingly recognized as a critical foundation for building reliable software systems. However, the need for specialized expertise to write precise specifi…

cs.NI2025

Can LLMs Forecast Internet Traffic from Social Media?

Jonatan Langlet, Mariano Scazzariello, Flavio Luciani +3

Societal events shape the Internet's behavior. The death of a prominent public figure, a software launch, or a major sports match can trigger sudden demand surges that overwhelm pe…

cs.LG2025

Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference

Mohammad Siavashi, Faezeh Keshmiri Dindarloo, Dejan Kostic +1

Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-se…