Harshit Khaitan

Director of AI Accelerators, Reality Labs, Facebook

Joined

September 2024

Names

Harshit Khaitan (Preferred)

Emails

****@meta.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

DBLP

Semantic Scholar

Career & Education History

Director of AI Accelerators

Reality Labs, Facebook (meta.com)

2019 – Present

Edge TPU Technical Lead

Hardware, Google (google.com)

2014 – 2019

Hardware Engineer

GPU, NVIDIA (nvidia.com)

2009 – 2014

MS student

Electrical and Computer Engineering, North Carolina State University (ncsu.edu)

2007 – 2008

Advisors, Relations & Conflicts

No relations added

Expertise

Machine Learning

Present

Artificial Intelligence

Present

ASIC Design

Present

Publications

CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill
Bradley McDanel, Steven Li, Harshit Khaitan
- Submitted to ICLR 2026
- Readers: Everyone
WiniQ: Accelerating Quantization-Aware Training of LLMs around Saddle Points
Dongyue Li, Zechun Liu, Kai Yi, Changsheng Zhao, Raghuraman Krishnamoorthi, Harshit Khaitan, Hongyang R. Zhang, Steven Li
- Submitted to ICLR 2026
- Readers: Everyone
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
Zhenyu Zhang, Zechun Liu, Yuandong Tian, Harshit Khaitan, Zhangyang Wang, Steven Li
- ICLR 2025
- Readers: Everyone
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
Zhenyu Zhang, Zechun Liu, Yuandong Tian, Harshit Khaitan, Zhangyang Wang, Steven Li
- ICLR 2025 Poster
- Readers: Everyone
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse
Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby R. Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, Vijay Janapa Reddi
- MLSys 2023
- Readers: Everyone
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse
Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby R. Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, Vijay Janapa Reddi
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- CoRR 2022
- Readers: Everyone
In-Datacenter Performance Analysis of a Tensor Processing Unit
Norman P. Jouppi, Cliff Young, Nishant Patil, David A. Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, Suresh Bhatia, Nan Boden, Al Borchers, Rick Boyle, Pierre-luc Cantin, Clifford Chao, Chris Clark, Jeremy Coriell, Mike Daley, Matt Dau, Jeffrey Dean, Ben Gelb, Tara Vazir Ghaemmaghami et al. (54 additional authors not shown)
- CoRR 2017
- Readers: Everyone
In-Datacenter Performance Analysis of a Tensor Processing Unit
Norman P. Jouppi, Cliff Young, Nishant Patil, David A. Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, Suresh Bhatia, Nan Boden, Al Borchers, Rick Boyle, Pierre-luc Cantin, Clifford Chao, Chris Clark, Jeremy Coriell, Mike Daley, Matt Dau, Jeffrey Dean, Ben Gelb, Tara Vazir Ghaemmaghami et al. (56 additional authors not shown)
- ISCA 2017
- Readers: Everyone

Co-Authors

View all 103 co-authors