activity
20242026
collaborators

5 papers

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

Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization

Amey Agrawal, Sameer Reddy, Satwik Bhattamishra +4

With the increase in the scale of Deep Learning (DL) training workloads in terms of compute resources and time consumption, the likelihood of encountering in-training failures rise…