Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens

Documenti analoghi

• ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference
  di: Zeng, Ziqian, et al.
  Pubblicazione: (2023)
• LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
  di: Shao, Wei, et al.
  Pubblicazione: (2025)
• SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
  di: Lu, Weikai, et al.
  Pubblicazione: (2025)
• Subkv: Quantizing Long Context KV Cache for Sub‐Billion Parameter Language Models on Edge Devices
  di: Ziqian Zeng, et al.
  Pubblicazione: (2025)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration
  di: Wu, Pengfei, et al.
  Pubblicazione: (2024)