Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant

Documenti analoghi

• Mixed Non-linear Quantization for Vision Transformers
  di: Kim, Gihwan, et al.
  Pubblicazione: (2024)
• QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention
  di: Oh, Sehyeon, et al.
  Pubblicazione: (2026)
• Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems
  di: Lee, Jemin, et al.
  Pubblicazione: (2023)
• Correction to “NEST‐C: A deep learning compiler framework for heterogeneous computing systems with artificial intelligence accelerators”
  di: Jeman Park, et al.
  Pubblicazione: (2024)
• QuantuneV2: Compiler-Based Local Metric-Driven Mixed Precision Quantization for Practical Embedded AI Applications
  di: Kim, Jeongseok, et al.
  Pubblicazione: (2025)