KV-CAR: KV Cache Compression using Autoencoders and KV Reuse in Large Language Models

Documenti analoghi

• Experts are all you need: A Composable Framework for Large Language Model Inference
  di: Sridharan, Shrihari, et al.
  Pubblicazione: (2025)
• Ev-Edge: Efficient Execution of Event-based Vision Algorithms on Commodity Edge Platforms
  di: Sridharan, Shrihari, et al.
  Pubblicazione: (2024)
• ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models
  di: Ramachandran, Akshat, et al.
  Pubblicazione: (2025)
• The Pitfalls of KV Cache Compression
  di: Chen, Alex, et al.
  Pubblicazione: (2025)
• CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing
  di: Wang, Yixuan, et al.
  Pubblicazione: (2025)