7 papers · 1 filter
TwinKV: A Composable Repair Pass for KV Cache Eviction via Pairwise Key Redundancy
Hong Chen, Yudong Zeng, Yongwei Huang +4
Long-context inference is bottlenecked by the memory footprint of the key-value (KV) cache, especially for small models under tight resource budgets. Existing KV cache eviction met…
SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching
Hong Chen, Xiang Liu, Bo Wang +5
The linear growth of Key-Value (KV) cache remains a bottleneck for multi-turn LLM deployment. Existing KV cache compression methods often fail to account for the structural propert…
DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
Xiang Liu, Xuming Hu, Xiaowen Chu +1
Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to im…
FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management
Xiang Liu, Hong Chen, Xuming Hu +1
Large Language Models (LLMs) are increasingly deployed in multi-turn conversational applications, where the management of the Key-Value (KV) Cache presents a significant bottleneck…
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
Xiang Liu, Zhenheng Tang, Hong Chen +6
While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the deg…
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
Xiang Liu, Zhenheng Tang, Peijie Dong +5
Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Althoug…