Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models
Chen Qiu, Ziwu Liu, Chao Fei +2
KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct executions fail nor why. We present KVDiagnosis, a diagnostic dataset and b…
cs.AI2026
CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference
Chao Fei, Guozhong Li, Chenxi Liu +1
Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnos…