MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping

Documenti analoghi

• HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
  di: Huang, Yushi, et al.
  Pubblicazione: (2024)
• A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms
  di: Gong, Ruihao, et al.
  Pubblicazione: (2024)
• EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models
  di: Jing, Linglin, et al.
  Pubblicazione: (2025)
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
  di: Lu, Xudong, et al.
  Pubblicazione: (2024)
• Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models
  di: Du, Jinyang, et al.
  Pubblicazione: (2026)