From the 1 of 9 linked papers with an AI index.
9 papers
ClusterBench: A Framework for Cluster-Wide Continuous Benchmarking and Regression Testing
Aditya Ujeniya, Jan Eitzinger, Thomas Gruber +2
Data centers need tooling that validates an entire installation rather than individual nodes, at acceptance and at regular intervals thereafter. This requires dispatching identical…
Architectural Trade-offs in the Energy-Efficient Era: A Comparative Study of power-capping NVIDIA H100 and H200
Aditya Ujeniya, Jan Eitzinger, Georg Hager +1
The paper compares NVIDIA H100 and H200 GPUs under different power caps, focusing on how memory bandwidth and power distribution affect performance per watt for compute‑bound and m…
Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
Bole Ma, Jan Eitzinger, Harald Koestler +1
Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides and reasoning iterates, yet every look-back re-…
Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
Bole Ma, Jan Eitzinger, Harald Köstler +1
Frontier LLMs increasingly decide what a query attends to with a sparse-attention indexer that picks a few KV-cache blocks per query: attention's unit is now a small, reusable chun…
Leyline: KV Cache Directives for Agentic Inference
Bole Ma, Jan Eitzinger, Harald Koestler
Modern KV cache management assumes the chatbot workload: prompts arrive once and the cache grows append-only, so prefix caching and forward-only eviction are correct by constructio…
Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory
Bole Ma, Jan Eitzinger, Harald Koestler +1
AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations: predictive sample placement,…