Scholar
Ramon Matas
Google Scholar ID: jqLlerkAAAAJ
Principal engineer @ nvidia
Computer Architecture
ML
HPC
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,937
H-index
8
i10-index
8
Publications
20
Co-authors
12
list available
Publications
2 items
Helix Parallelism: Rethinking Sharding Strategies for Interactive Multi-Million-Token LLM Decoding
2025
Cited
0
Beyond the Buzz: A Pragmatic Take on Inference Disaggregation
2025
Cited
0
Co-authors
8 total
Paul N Whatmough
Qualcomm AI Research, Harvard University
Venkatesh Saligrama
AI Professor and Amazon Scholar
Durmus Alp Emre Acar
Boston University
Yue Zhao
Square Machine Learning Engineer
Chuteng Zhou
Arm Inc. / MIT
Igor Fedorov
Meta
Vijay Janapa Reddi
Harvard University
Colby Banbury
Senior Researcher, Microsoft