collaborators

6 papers

cs.DC2026

PCCL: Process Group-Aware Scalable and Generic Collective Algorithm Synthesizer

William Won, Kartik Lakhotia, Madhu Kumar +2

Distributed machine learning has become increasingly important due to the massive scale of large-scale generative models. Both model parameters and data are distributed across many…

cs.LG2026

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

Hanjiang Wu, Abhimanyu Rajeshkumar Bambhaniya, Sarbartha Banerjee +9

Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-pre…

cs.AR2026

MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference

Abhimanyu Rajeshkumar Bambhaniya, Hanjiang Wu, Suvinay Subramanian +8

Modern LLM serving now spans multi-stage pipelines including RAG retrieval and KV cache reuse, each with distinct compute, memory, and latency demands. Inference engines expose a l…

cs.AR2025

FRED: Flexible REduction-Distribution Interconnect and Communication Implementation for Wafer-Scale Distributed Training of DNN Models

Saeed Rashidi, William Won, Sudarshan Srinivasan +2

Distributed Deep Neural Network (DNN) training is a technique to reduce the training overhead by distributing the training tasks into multiple accelerators, according to a parallel…

cs.AR2025

Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models

Abhimanyu Bambhaniya, Ritik Raj, Geonhwa Jeong +6

Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these gigantic models effi…

cs.NI2025

Towards Easy and Realistic Network Infrastructure Testing for Large-scale Machine Learning

Jinsun Yoo, ChonLam Lao, Lianjie Cao +4

This paper lays the foundation for Genie, a testing framework that captures the impact of real hardware network behavior on ML workload performance, without requiring expensive GPU…