Author

Aashaka Shah

Observed name: Shah, Aashaka

Institution: Microsoft (United States)

Observed institutions: Microsoft (United States), Indian Institute of Technology Roorkee, The University of Texas at Austin

ORCID: 0009-0004-0628-4515

Observed ORCID: 0009-0004-0628-4515

OpenAlex ID: A5023546887

Splitwise: Efficient Generative LLM Inference Using Phase Splitting

2024 · Pratyush Patel, Esha Choukse, et al. · Proceedings - International Symposium on Computer Architecture/Proceedings · 300

Empowering Light Nodes in Blockchains with Block Summarization

2018 · Asutosh Palai, Meet Vora, et al. · IFIP International Conference on New Technologies, Mobility and Security (NTMS) · 79

Analyzing the Impact of GDPR on Storage Systems

2019 · Shah, Aashaka, Banakar, Vinay, et al. · arXiv (Cornell University) · 31

TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches

2021 · Shah, Aashaka, Chidambaram, Vijay, et al. · arXiv (Cornell University) · 24

Rainblock: Faster Transaction Processing in Public Blockchains

2019 · Ponnapalli, Soujanya, Shah, Aashaka, et al. · arXiv (Cornell University) · 22

Memory Optimization for Deep Networks

2020 · Shah, Aashaka, Wu, Chao-Yuan, et al. · arXiv (Cornell University) · 11

Scalable and Efficient Data Authentication for Decentralized Systems.

2019 · Soujanya Ponnapalli, Aashaka Shah, et al. · 10

Splitwise: Efficient generative LLM inference using phase splitting

2023 · Patel, Pratyush, Choukse, Esha, et al. · arXiv (Cornell University) · 6

MSCCL++: Rethinking GPU Communication Abstractions for AI Inference

2026 · Changho Hwang, Peng Cheng, et al. · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · 5

Splitwise: Efficient Generative LLM Inference Using Phase Splitting

2025 · Esha Choukse, Pratyush Patel, et al. · IEEE Micro · 5

Synthesizing Collective Communication Algorithms for Heterogeneous Networks with TACCL

2021 · Aashaka Shah, Vijay Chidambaram, et al. · arXiv (Cornell University) · 2

CacheSmith: Accurate RAG Serving under Latency SLOs with Adaptive KV Reuse

2026 · Ma, Xinyue, Lee, Damin, et al. · arXiv (Cornell University)

MSCCL++ ASPLOS'26 Artifact

2026 · Hwang, Changho, Cheng, Peng, et al. · Zenodo (CERN European Organization for Nuclear Research)

Works count: 15

Citation count: 495

H-index: 7

I10-index: 7