20 citations · 36 across the 6 of their papers we have counts for
6 papers
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…
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…
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…
LACS: Learning-Augmented Algorithms for Carbon-Aware Resource Scaling with Uncertain Demand
Roozbeh Bostandoost, Adam Lechowicz, Walid A. Hanafy +3
Motivated by an imperative to reduce the carbon emissions of cloud data centers, this paper studies the online carbon-aware resource scaling problem with unknown job lengths (OCSU)…
The War of the Efficiencies: Understanding the Tension between Carbon and Energy Optimization
Walid A. Hanafy, Roozbeh Bostandoost, Noman Bashir +3
Major innovations in computing have been driven by scaling up computing infrastructure, while aggressively optimizing operating costs. The result is a network of worldwide datacent…
Near-optimal Online Algorithms for Joint Pricing and Scheduling in EV Charging Networks
Roozbeh Bostandoost, Bo Sun, Carlee Joe-Wong +1
With the rapid acceleration of transportation electrification, public charging stations are becoming vital infrastructure in a smart sustainable city to provide on-demand electric…