SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

Documenti analoghi

• DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
  di: Huang, You-Liang, et al.
  Pubblicazione: (2026)
• Training-Free Activation Sparsity in Large Language Models
  di: Liu, James, et al.
  Pubblicazione: (2024)
• SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping
  di: Lu, Yu-Chen, et al.
  Pubblicazione: (2025)
• Leveraging Large Language Models for Entity Matching
  di: Huang, Qianyu, et al.
  Pubblicazione: (2024)
• TLoRA: Task-aware Low Rank Adaptation of Large Language Models
  di: Lin, Weicheng, et al.
  Pubblicazione: (2026)