InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation

Documenti analoghi

• InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
  di: Xiao, Chaojun, et al.
  Pubblicazione: (2024)
• NOSA: Native and Offloadable Sparse Attention
  di: Huang, Yuxiang, et al.
  Pubblicazione: (2025)
• APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
  di: Huang, Yuxiang, et al.
  Pubblicazione: (2026)
• DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
  di: Song, Chenyang, et al.
  Pubblicazione: (2026)
• APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
  di: Huang, Yuxiang, et al.
  Pubblicazione: (2025)