LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction

Documenti analoghi

• LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation
  di: Shen, Yiqun, et al.
  Pubblicazione: (2025)
• Taming the Fragility of KV Cache Eviction in LLM Inference
  di: Feng, Yuan, et al.
  Pubblicazione: (2025)
• Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
  di: Miao, Ruijie, et al.
  Pubblicazione: (2026)
• Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  di: Feng, Yuan, et al.
  Pubblicazione: (2024)
• EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving
  di: Feng, Shaoting, et al.
  Pubblicazione: (2025)