2 papers
cs.DC2026
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…
cs.DC2026
Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving
Bole Ma, Jan Eitzinger, Harald Köstler
Agentic LLM workloads put bit-identical tokens at shifted positions every turn, voiding prefix caches at the first byte of divergence. Operators report cache-hit regressions rangin…