AHASD: Asynchronous Heterogeneous Architecture for LLM Adaptive Drafting Speculative Decoding on Mobile Devices

Documenti analoghi

• Survey on Characterizing and Understanding GNNs from a Computer Architecture Perspective
  di: Wu, Meng, et al.
  Pubblicazione: (2024)
• StreamDCIM: A Tile-based Streaming Digital CIM Accelerator with Mixed-stationary Cross-forwarding Dataflow for Multimodal Transformer
  di: Qin, Shantian, et al.
  Pubblicazione: (2025)
• Multilayer Dataflow: Orchestrate Butterfly Sparsity to Accelerate Attention Computation
  di: Wu, Haibin, et al.
  Pubblicazione: (2024)
• Accelerating Mini-batch HGNN Training by Reducing CUDA Kernels
  di: Wu, Meng, et al.
  Pubblicazione: (2024)
• LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization
  di: He, Siyuan, et al.
  Pubblicazione: (2025)