2 papers
cs.DC2026
Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs
Jihao Xin, Tian Lyu, Qilong Pan +2
Post-training compression reduces LLM parameter counts but often produces irregular tensor dimensions that degrade GPU performance -- a phenomenon we call \emph{dimensional misalig…
cs.LG2026
RAP: KV-Cache Compression via RoPE-Aligned Pruning
Jihao Xin, Tian Lyu, David Keyes +2
Long-context inference in large language models (LLMs) is bottlenecked by the memory and compute of the key-value (KV) cache. Structured pruning is a direct way to shrink it: dropp…