EVA: Recasting LLM Decoding into GEMM via an Efficient Vector Quantization Architecture

Documenti analoghi

• EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
  di: Duan, Bowen, et al.
  Pubblicazione: (2026)
• Transitive Array: An Efficient GEMM Accelerator with Result Reuse
  di: Guo, Cong, et al.
  Pubblicazione: (2025)
• FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processing
  di: Fu, Yuzhe, et al.
  Pubblicazione: (2025)
• Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models
  di: Wei, Chiyue, et al.
  Pubblicazione: (2025)
• Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication
  di: Shan, Haoxuan, et al.
  Pubblicazione: (2025)