VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits

Documenti analoghi

• ComplexFormer: Disruptively Advancing Transformer Inference Ability via Head-Specific Complex Vector Attention
  di: Shao, Jintian, et al.
  Pubblicazione: (2025)
• Nitrogen and phosphorus dynamics and nutrient resorption of rhizophora mangle leaves in south Florida, USA
  di: Lin, YiMing
  Pubblicazione: (2007)
• Logits-Based Finetuning
  di: Li, Jingyao, et al.
  Pubblicazione: (2025)
• CommVQ: Commutative Vector Quantization for KV Cache Compression
  di: Li, Junyan, et al.
  Pubblicazione: (2025)
• An Analysis of Logit Learning with the r-Lambert Function
  di: Gavin, Rory, et al.
  Pubblicazione: (2024)