Comments and Discussion

Authors: Krishnamurthy, Arvind, Rajan, Raghuram

Source: Brookings Papers on Economic Activity. 2024(1):390-411

Availability: https://muse.jhu.edu/article/944614

Panel on Shrinking the Federal Reserve Balance Sheet

Authors: Krishnamurthy, Arvind, Ludvigson, Sydney C., Wright, Jonathan H.

Source: Brookings Papers on Economic Activity. 2022(2):231-280

Availability: https://muse.jhu.edu/article/901273

Lessons for Policy from Research

Authors: Krishnamurthy, Arvind

Source: Brookings Papers on Economic Activity. 2022(2):233-242

Availability: https://muse.jhu.edu/article/901801

SLOs-Serve: Optimized Serving of Multi-SLO LLMs

Authors: Chen, Siyuan, Jia, Zhipeng, Khan, Samira, Krishnamurthy, Arvind, Gibbons, Phillip B.

Subject Terms: Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2504.08784

TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval

Authors: Lin, Chien-Yu, Kamahori, Keisuke, Liu, Yiyu, Shi, Xiaoxiang, Kashyap, Madhav, Gu, Yile, Shao, Rulin, Ye, Zihao, Zhu, Kan, Wang, Stephanie, Krishnamurthy, Arvind, Kadekodi, Rohan, Ceze, Luis, Kasikci, Baris

Subject Terms: Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2502.20969

Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs

Authors: Zhu, Kan, Tang, Tian, Xu, Qinyu, Gu, Yile, Zeng, Zhichen, Kadekodi, Rohan, Zhao, Liangyu, Li, Ang, Krishnamurthy, Arvind, Kasikci, Baris

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2502.12216

Corporate Debt Overhang and Credit Policy

Authors: Brunnermeier, Markus, Krishnamurthy, Arvind

Source: Brookings Papers on Economic Activity. 2020(2):447-502

Availability: https://muse.jhu.edu/article/787115

EchoLM: Accelerating LLM Serving with Real-time Knowledge Distillation

Authors: Yu, Yifan, Gan, Yu, Tsai, Lillian, Sarda, Nikhil, Shen, Jiaming, Zhou, Yanqi, Krishnamurthy, Arvind, Lai, Fan, Levy, Henry M., Culler, David

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2501.12689

FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Authors: Ye, Zihao, Chen, Lequn, Lai, Ruihang, Lin, Wuwei, Zhang, Yineng, Wang, Stephanie, Chen, Tianqi, Kasikci, Baris, Grover, Vinod, Krishnamurthy, Arvind, Ceze, Luis

Subject Terms: Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2501.01005

Comments and Discussion

Authors: Eggertsson, Gauti B., Krishnamurthy, Arvind

Source: Brookings Papers on Economic Activity. 2019(1):55-76

Availability: https://muse.jhu.edu/article/741597

Comments and Discussion

Authors: Krishnamurthy, Arvind

Source: Brookings Papers on Economic Activity. 2018(1):414-428

Availability: https://muse.jhu.edu/article/709010

NanoFlow: Towards Optimal Large Language Model Serving Throughput

Authors: Zhu, Kan, Zhao, Yilong, Zhao, Liangyu, Zuo, Gefei, Gu, Yile, Xie, Dedong, Gao, Yufei, Xu, Qinyu, Tang, Tian, Ye, Zihao, Kamahori, Keisuke, Lin, Chien-Yu, Wang, Stephanie, Krishnamurthy, Arvind, Kasikci, Baris

Subject Terms: Computer Science - Distributed, Parallel, and Cluster Computing

Access URL: http://arxiv.org/abs/2408.12757

Relational Network Verification

Authors: Xu, Xieyang, Yuan, Yifei, Kincaid, Zachary, Krishnamurthy, Arvind, Mahajan, Ratul, Walker, David, Zhai, Ennan

Subject Terms: Computer Science - Networking and Internet Architecture

Access URL: http://arxiv.org/abs/2403.17277

Laconic: Streamlined Load Balancers for SmartNICs

Authors: Cui, Tianyi, Zhao, Chenxingyu, Zhang, Wei, Zhang, Kaiyuan, Krishnamurthy, Arvind

Subject Terms: Computer Science - Networking and Internet Architecture

Access URL: http://arxiv.org/abs/2403.11411

ForestColl: Throughput-Optimal Collective Communications on Heterogeneous Network Fabrics

Authors: Zhao, Liangyu, Maleki, Saeed, Yang, Ziyue, Pourreza, Hossein, Krishnamurthy, Arvind

Subject Terms: Computer Science - Networking and Internet Architecture, Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2402.06787

Efficient Credit Policies in a Housing Debt Crisis

Authors: Eberly, Janice, Krishnamurthy, Arvind

Source: Brookings Papers on Economic Activity. 2014(2):73-136

Availability: https://muse.jhu.edu/article/577364

Bringing Reconfigurability to the Network Stack

Authors: Narayan, Akshay, Panda, Aurojit, Alizadeh, Mohammad, Balakrishnan, Hari, Krishnamurthy, Arvind, Shenker, Scott

Subject Terms: Computer Science - Networking and Internet Architecture

Access URL: http://arxiv.org/abs/2311.07753

The Effects of Quantitative Easing on Interest Rates: Channels and Implications for Policy

Authors: Krishnamurthy, Arvind, Vissing-Jorgensen, Annette

Source: Brookings Papers on Economic Activity. 2011(2):215-287

Availability: https://muse.jhu.edu/article/475020

Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

Authors: Zhao, Yilong, Lin, Chien-Yu, Zhu, Kan, Ye, Zihao, Chen, Lequn, Zheng, Size, Ceze, Luis, Krishnamurthy, Arvind, Chen, Tianqi, Kasikci, Baris

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2310.19102

Punica: Multi-Tenant LoRA Serving

Authors: Chen, Lequn, Ye, Zihao, Wu, Yongji, Zhuo, Danyang, Ceze, Luis, Krishnamurthy, Arvind

Subject Terms: Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2310.18547