Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

Documenti analoghi

• Learning to be Smooth: An End-to-End Differentiable Particle Smoother
  di: Younis, Ali, et al.
  Pubblicazione: (2025)
• INT-FlashAttention: Enabling Flash Attention for INT8 Quantization
  di: Chen, Shimao, et al.
  Pubblicazione: (2024)
• TrainMover: An Interruption-Resilient Runtime for ML Training
  di: Lao, ChonLam, et al.
  Pubblicazione: (2024)
• SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
  di: Zhang, Jintao, et al.
  Pubblicazione: (2024)
• Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging
  di: Liu, Guisong, et al.
  Pubblicazione: (2026)