QAQ: Quality Adaptive Quantization for LLM KV Cache

Documenti analoghi

• CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
  di: Qin, Ziran, et al.
  Pubblicazione: (2025)
• WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference
  di: Zuo, Youhui, et al.
  Pubblicazione: (2025)
• AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models
  di: Su, Zunhai, et al.
  Pubblicazione: (2025)
• KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
  di: Chen, Jian, et al.
  Pubblicazione: (2026)
• Accurate KV Cache Quantization with Outlier Tokens Tracing
  di: Su, Yi, et al.
  Pubblicazione: (2025)