Gerhard Wellein
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Distributed×1AI×1Networking×1
Frequent co-authors
Research Timeline
2026
Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
The paper proposes moving the query instead of the KV-cache during cross-instance attention, demonstrating that this approach is significantly cheaper than moving the cache, especially on modern GPU fabrics.
Highlighted terms show continued research focus across papers