activity
20242026
most citedLayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data

1 citations · 1 across the 2 of their papers we have counts for

collaborators

8 papers

cs.DC20261 cited

LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data

Debopam Sanyal, Hongjie Chen, Alexey Tumanov +1

Modern multimedia machine learning workloads increasingly store large-scale datasets in cloud object storage services such as AWS S3. How these samples are physically organized in…

cs.DC2026

Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving

Amey Agrawal, Mayank Yadav, Sukrit Kumar +9

Deploying LLMs efficiently requires testing hundreds of serving configurations, but evaluating each one on a GPU cluster takes hours and costs thousands of dollars. Discrete-event…

cs.LG2025

No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha

Amey Agrawal, Haoran Qiu, Junda Chen +6

Deploying million-token Large Language Models (LLMs) is challenging because production workloads are highly heterogeneous, mixing short queries and long documents. This heterogenei…

cs.LG2025

Maya: Optimizing Deep Learning Training Workloads using GPU Runtime Emulation

Srihas Yarlagadda, Amey Agrawal, Elton Pinto +6

Training large foundation models costs hundreds of millions of dollars, making deployment optimization critical. Current approaches require machine learning engineers to manually c…

cs.LG2025

On Evaluating Performance of LLM Inference Serving Systems

Amey Agrawal, Nitin Kedia, Anmol Agarwal +5

The rapid evolution of Large Language Model (LLM) inference systems has yielded significant efficiency improvements. However, our systematic analysis reveals that current evaluatio…

cs.LG2024

Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems

Amey Agrawal, Anmol Agarwal, Nitin Kedia +5

Serving large language models (LLMs) in production can incur substantial costs, which has prompted recent advances in inference system optimizations. Today, these systems are evalu…