kv cache compression

6 papers

• Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs
• MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference
• Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
• R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
• SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
• TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup