6 papers
RAP: KV-Cache Compression via RoPE-Aligned Pruning
Jihao Xin, Tian Lyu, David Keyes +2
Long-context inference in large language models (LLMs) is bottlenecked by the memory and compute of the key-value (KV) cache. Structured pruning is a direct way to shrink it: dropp…
MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability
Tie Ma, Yixi Chen, Vaastav Anand +8
We present MAESTRO, an evaluation suite for the testing, reliability, and observability of LLM-based MAS. MAESTRO standardizes MAS configuration and execution through a unified int…
A Network Arena for Benchmarking AI Agents on Network Troubleshooting
Zhihao Wang, Alessandro Cornacchia, Alessio Sacco +3
Agentic systems, powered by Large Language Models (LLMs), assist network engineers with network configuration synthesis and network troubleshooting tasks. For network troubleshooti…
DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
Alessandro Cornacchia, Vaastav Anand, Muhammad Bilal +2
Agentic AI applications increasingly rely on multiple agents with distinct roles, specialized tools, and access to memory layers to solve complex tasks -- closely resembling servic…
Protecting Confidentiality, Privacy and Integrity in Collaborative Learning
Dong Chen, Alice Dethise, Istemi Ekin Akkus +6
A collaboration between dataset owners and model owners is needed to facilitate effective machine learning (ML) training. During this collaboration, however, dataset owners and mod…
OffRAC: Offloading Through Remote Accelerator Calls
Ziyi Yang, Krishnan B. Iyer, Yixi Chen +4
Modern applications increasingly demand ultra-low latency for data processing, often facilitated by host-controlled accelerators like GPUs and FPGAs. However, significant delays re…