CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

Documenti analoghi

• DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution
  di: Hu, Yunhai, et al.
  Pubblicazione: (2026)
• SD$^2$: Self-Distilled Sparse Drafters
  di: Lasby, Mike, et al.
  Pubblicazione: (2025)
• DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
  di: Liu, Zining, et al.
  Pubblicazione: (2026)
• DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding
  di: Hu, Yunhai, et al.
  Pubblicazione: (2025)
• REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
  di: Lasby, Mike, et al.
  Pubblicazione: (2025)