E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity

Documenti analoghi

• Spatial Re-parameterization for N:M Sparsity
  di: Zhang, Yuxin, et al.
  Pubblicazione: (2023)
• FPGA Co-Design for Efficient N:M Sparse and Quantized Model Inference
  di: Hsieh, Fen-Yu, et al.
  Pubblicazione: (2025)
• Sparsity-Accelerated Training for Large Language Models
  di: Ma, Da, et al.
  Pubblicazione: (2024)
• Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models
  di: An, Tai, et al.
  Pubblicazione: (2025)
• Exploring Forgetting in Large Language Model Pre-Training
  di: Liao, Chonghua, et al.
  Pubblicazione: (2024)