DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding

Documenti analoghi

• DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning
  di: Zarch, Hossein Entezari, et al.
  Pubblicazione: (2025)
• KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation
  di: Jiang, Chaoyi, et al.
  Pubblicazione: (2024)
• DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
  di: Gao, Lei, et al.
  Pubblicazione: (2025)
• CADC: Encoding User-Item Interactions for Compressing Recommendation Model Training Data
  di: Zarch, Hossein Entezari, et al.
  Pubblicazione: (2024)
• MARché: Fast Masked Autoregressive Image Generation with Cache-Aware Attention
  di: Jiang, Chaoyi, et al.
  Pubblicazione: (2025)