類似資料

• Jenga: Effective Memory Management for Serving LLM with Heterogeneity
  著者:: Zhang, Chen, 等
  出版事項: (2025)
• Speculative Decoding: Performance or Illusion?
  著者:: Liu, Xiaoxuan, 等
  出版事項: (2025)
• Online Speculative Decoding
  著者:: Liu, Xiaoxuan, 等
  出版事項: (2023)
• Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection
  著者:: Park, Jongseok, 等
  出版事項: (2026)
• Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution
  著者:: Park, Jongseok, 等
  出版事項: (2026)