D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Documenti analoghi

• MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference
  di: Wan, Zhongwei, et al.
  Pubblicazione: (2025)
• LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference
  di: Wan, Zhongwei, et al.
  Pubblicazione: (2024)
• MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation
  di: Wan, Zhongwei, et al.
  Pubblicazione: (2024)
• Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS
  di: Dou, Alex ZH, et al.
  Pubblicazione: (2025)
• SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
  di: Wang, Xin, et al.
  Pubblicazione: (2024)