TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control

Documenti analoghi

• Oscillation-Reduced MXFP4 Training for Vision Transformers
  di: Chen, Yuxiang, et al.
  Pubblicazione: (2025)
• Accurate INT8 Training Through Dynamic Block-Level Fallback
  di: Zhang, Pengle, et al.
  Pubblicazione: (2025)
• SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
  di: Zhang, Jintao, et al.
  Pubblicazione: (2024)
• Deterministic Differentiable Structured Pruning for Large Language Models
  di: Huang, Weiyu, et al.
  Pubblicazione: (2026)
• Dissecting Outlier Dynamics in LLM NVFP4 Pretraining
  di: Dong, Peijie, et al.
  Pubblicazione: (2026)