Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics

Documenti analoghi

• Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
  di: Sengupta, Ayan, et al.
  Pubblicazione: (2025)
• Compression Laws for Large Language Models
  di: Sengupta, Ayan, et al.
  Pubblicazione: (2025)
• You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
  di: Sengupta, Ayan, et al.
  Pubblicazione: (2025)
• Position: Enough of Scaling LLMs! Lets Focus on Downscaling
  di: Goel, Yash, et al.
  Pubblicazione: (2025)
• The Art of Scaling Test-Time Compute for Large Language Models
  di: Agarwal, Aradhye, et al.
  Pubblicazione: (2025)