GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units

Documenti analoghi

• XAMBA: Enabling Efficient State Space Models on Resource-Constrained Neural Processing Units
  di: Das, Arghadip, et al.
  Pubblicazione: (2025)
• FlexNN: A Dataflow-aware Flexible Deep Learning Accelerator for Energy-Efficient Edge Devices
  di: Raha, Arnab, et al.
  Pubblicazione: (2024)
• SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference
  di: Parvathy, Aradhana Mohan, et al.
  Pubblicazione: (2026)
• Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator
  di: Ramachandran, Akshat, et al.
  Pubblicazione: (2025)
• StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign
  di: Wu, Michael, et al.
  Pubblicazione: (2025)