Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations

Documenti analoghi

• TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization
  di: Yao, Dingyu, et al.
  Pubblicazione: (2025)
• Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
  di: Gu, Naibin, et al.
  Pubblicazione: (2024)
• VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
  di: Yao, Dingyu, et al.
  Pubblicazione: (2025)
• Think, But Don't Overthink: Reproducing Recursive Language Models
  di: Wang, Daren
  Pubblicazione: (2026)
• DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts
  di: Feng, Yuchen, et al.
  Pubblicazione: (2025)