Ngā tūemi rite

• InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
  mā: Zhao, Weilin, me ētahi atu.
  I whakaputaina: (2025)
• Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules
  mā: Xiao, Chaojun, me ētahi atu.
  I whakaputaina: (2023)
• Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices
  mā: Huang, Yuxiang, me ētahi atu.
  I whakaputaina: (2024)
• Exploring the Benefit of Activation Sparsity in Pre-training
  mā: Zhang, Zhengyan, me ētahi atu.
  I whakaputaina: (2024)
• APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
  mā: Huang, Yuxiang, me ētahi atu.
  I whakaputaina: (2025)