Scaling Long-Context LLMs via Unified KV Cache Optimization: A Comparative Study of Paged Attention and Quantization

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1. 1QAQ: Quality Adaptive Quantization for LLM KV Cache2024 · 3 citations
2. 2SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models2024
3. 3WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More2024 · 2 citations
4. 4KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization2024 · 1 citations
5. 5KVCompose: Efficient Structured KV Cache Compression with Composite Tokens2025