Follow
Sudipta Sengupta
Sudipta Sengupta
Vice President & Distinguished Scientist, Amazon AWS
Verified email at amazon.com - Homepage
Title
Cited by
Year
Interactive assistance for executing natural language queries to data sets
RM Nallapati, Z Wang, B Xiang, P Ng, YH Wang, M Karnik, N Li, ...
US Patent 12,007,988, 2024
2024
Hydride: A Retargetable and Extensible Synthesis-based Compiler for Modern Hardware Architectures
A Kothari, AR Noor, M Xu, H Uddin, D Baronia, S Baziotis, V Adve, ...
Proceedings of the 29th ACM International Conference on Architectural …, 2024
2024
BASS: Batched Attention-optimized Speculative Sampling
H Qian, SK Gonugondla, S Ha, M Shang, SK Gouda, R Nallapati, ...
arXiv preprint arXiv:2404.15778, 2024
2024
Fault-tolerant accelerator based inference service
S Sengupta, PCS Perumalla, DR Divakaruni, N BShara, LP Dirac, B Saha, ...
US Patent 11,960,935, 2024
2024
Bifurcated attention for single-context large-batch sampling
B Athiwaratkun, SK Gonugondla, SK Gouda, H Qian, H Ding, Q Sun, ...
arXiv preprint arXiv:2403.08845, 2024
2024
Random token segmentation for training next token prediction models
Z Wang, T Yuchen, M Shang, P Athiwaratkun, M Tan, P Bhatia, AO Arnold, ...
US Patent App. 17/847,118, 2023
2023
Programmatically generating evaluation data sets for code generation models
P Athiwaratkun, Z Lin, R Keerthi, Z Wang, T Yuchen, H Ding, SRA Bontala, ...
US Patent App. 17/847,113, 2023
12023
Validating and providing proactively generated code suggestions
SA Selvaraj, Q Yu, VRR Swamireddy, M Lee, L Gao, W Fang, ...
US Patent App. 17/847,112, 2023
2023
Constrained prefix matching for generating next token predictions
P Athiwaratkun, T Yuchen, M Shang, Z Wang, RM Nallapati, P Bhatia, ...
US Patent App. 17/847,115, 2023
2023
Use of batch mode function execution in database engines to enable efficient calls to remote services
S Stefani, S Sengupta, JD Mangas, JL Finnerty, RB Shah, SV Maru
US Patent 11,797,535, 2023
12023
Machine learning inference calls for database query processing
S Sangil, Y Yoon, KK Gupta, S Krishnamurthy, S Stefani, S Sengupta, ...
US Patent 11,775,868, 2023
2023
Providing query restatements for explaining natural language query results
J Wang, Z Wang, SP Revadigar, RM Nallapati, B Xiang, S Sengupta, ...
US Patent 11,726,994, 2023
12023
Multiple stage filtering for natural language query processing pipelines
J Wang, Z Wang, SP Revadigar, RM Nallapati, B Xiang, SM Ash, T Jones, ...
US Patent 11,726,997, 2023
22023
[Industry] A Static Evaluation of Code Completion by Large Language Models
H Ding, V Kumar, Y Tian, Z Wang, R Kwiatkowski, X Li, MK Ramanathan, ...
The 61st Annual Meeting Of The Association For Computational Linguistics, 2023
2023
Neural network training under memory restraint
S Sengupta, RR Huang, R Diamant, V Vivekaja
US Patent App. 18/112,036, 2023
2023
A static evaluation of code completion by large language models
H Ding, V Kumar, Y Tian, Z Wang, R Kwiatkowski, X Li, MK Ramanathan, ...
arXiv preprint arXiv:2306.03203, 2023
52023
Neural network training under memory restraint
S Sengupta, RR Huang, R Diamant, V Vivekraja
US Patent 11,610,128, 2023
2023
Interactive assistance for executing natural language queries to data sets
RM Nallapati, Z Wang, B Xiang, P Ng, YH Wang, M Karnik, N Li, ...
US Patent 11,604,794, 2023
22023
Attached accelerator based inference service
S Sengupta, PCS Perumalla, DR Divakaruni, N BShara, LP Dirac, B Saha, ...
US Patent 11,599,821, 2023
2023
On io-efficient attention mechanisms: Context-aware bifurcated attention and the generalized multi-group attention
B Athiwaratkun, SK Gonugondla, SK Gouda, H Qian, H Ding, Q Sun, ...
Workshop on Efficient Systems for Foundation Models@ ICML2023, 2023
12023
The system can't perform the operation now. Try again later.
Articles 1–20