3 papers
cs.LG2026
MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference
Michael Wang, Keith Li, Roozbeh Bostandoost
Key--value (KV) cache compression is an effective way to reduce the memory overhead of large language model (LLM) inference, particularly for long-context workloads. However, exist…
cs.DC2025
Quantifying the Carbon Reduction of DAG Workloads: A Job Shop Scheduling Perspective
Roozbeh Bostandoost, Adam Lechowicz, Walid A. Hanafy +2
Carbon-aware schedulers aim to reduce the operational carbon footprint of data centers by running flexible workloads during periods of low carbon intensity. Most schedulers treat w…
cs.DC2025
A Performance Analyzer for a Public Cloud's ML-Augmented VM Allocator
Roozbeh Bostandoost, Pooria Namyar, Siva Kesava Reddy Kakarla +8
Cloud operators increasingly deploy multiple ML models in their VM allocation pipelines. In such settings, individually benign predictions can shift and compound, severely degradin…