Scholar
Alexey Tumanov
Google Scholar ID: 7P-gZioAAAAJ
Associate Professor, Georgia Institute of Technology
Systems for ML
soft real-time ML
LLM inference
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
5,787
H-index
26
i10-index
33
Publications
20
Co-authors
28
list available
Contact
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
8 items
Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving
arXiv.org · 2026
Cited
0
On Evaluating Performance of LLM Inference Serving Systems
2025
Cited
0
Maya: Optimizing Deep Learning Training Workloads using Emulated Virtual Accelerators
2025
Cited
0
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
2025
Cited
0
Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning
arXiv.org · 2024
Cited
0
Mnemosyne: Parallelization Strategies for Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations
arXiv.org · 2024
Cited
2
PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off
2023
Cited
0
ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation
arXiv.org · 2023
Cited
2
Resume (English only)
Co-authors
28 total
Greg Ganger
Jatras Professor, Carnegie Mellon University
Co-author 2
Ion Stoica
Professor of Computer Science, UC Berkeley
Joseph E. Gonzalez
Professor of Computer Science, UC Berkeley
Co-author 5
Co-author 6
Co-author 7
Co-author 8
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up