Midhilesh Elavazhagan

According to our database, Midhilesh Elavazhagan authored at least 5 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

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, Tuhin Khare, Sudarshan Srinivasan, Suvinay Subramanian, Souvik Kundu, Madhu Kumar, Midhilesh Elavazhagan, William Won, Amir Yazdanbakhsh, Tushar Krishna

CoRR, May, 2026

2025

Understanding and Optimizing Multi-Stage AI Inference Pipelines.

Abhimanyu Rajeshkumar Bambhaniya, Hanjiang Wu, Suvinay Subramanian, Sudarshan Srinivasan, Souvik Kundu, Amir Yazdanbakhsh, Midhilesh Elavazhagan, Madhu Kumar, Tushar Krishna

CoRR, April, 2025

2024

Demystifying Platform Requirements for Diverse LLM Inference Use Cases.

Abhimanyu Bambhaniya, Ritik Raj, Geonhwa Jeong, Souvik Kundu, Sudarshan Srinivasan, Midhilesh Elavazhagan, Madhu Kumar, Tushar Krishna

CoRR, 2024

TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning.

William Won, Midhilesh Elavazhagan, Sudarshan Srinivasan, Swati Gupta, Tushar Krishna

Proceedings of the 57th IEEE/ACM International Symposium on Microarchitecture, 2024

2023

TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Training.

William Won, Midhilesh Elavazhagan, Sudarshan Srinivasan, Ajaya Durg, Swati Gupta, Tushar Krishna

CoRR, 2023