LeanK: Learnable K Cache Channel Pruning for Efficient Decoding

Documenti analoghi

• Accelerating Prefilling via Decoding-time Contribution Sparsity
  di: He, Zhiyuan, et al.
  Pubblicazione: (2025)
• Position Engineering: Boosting Large Language Models through Positional Information Manipulation
  di: He, Zhiyuan, et al.
  Pubblicazione: (2024)
• SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
  di: Liao, Huanxuan, et al.
  Pubblicazione: (2025)
• MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
  di: Li, Wenxuan, et al.
  Pubblicazione: (2025)
• VL Norm: Rethink Loss Aggregation in RLVR
  di: He, Zhiyuan, et al.
  Pubblicazione: (2025)