Scholar
Gerhard Wellein
Google Scholar ID: Fk1KSNMAAAAJ
Friedrich-Alexander-Universität Erlangen-Nürnberg
HPC
Performance Modelling
Performance Engineering
Sparse Solvers and Kernels
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3,707
H-index
26
i10-index
73
Publications
20
Co-authors
0
Contact
Email
gerhard.wellein@fau.de
Publications
12 items
Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
2026
Cited
0
Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
2026
Cited
0
Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory
2026
Cited
0
The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
2026
Cited
0
Safety and accuracy follow different scaling laws in clinical large language models
2026
Cited
0
Architectural Trade-offs in the Energy-Efficient Era: A Comparative Study of power-capping NVIDIA H100 and H200
2026
Cited
0
Wattlytics: A Web Platform for Co-Optimizing Performance, Energy, and TCO in HPC Clusters
2026
Cited
0
AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models
2026
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
