GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

Documenti analoghi

• Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction
  di: Li, Yuanzhe, et al.
  Pubblicazione: (2026)
• FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference
  di: Wang, Dongwei, et al.
  Pubblicazione: (2025)
• Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
  di: Wang, Dongwei, et al.
  Pubblicazione: (2024)
• Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts
  di: Wu, Haoyuan, et al.
  Pubblicazione: (2025)
• $\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
  di: Chen, Guanjie, et al.
  Pubblicazione: (2024)