ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerance

Documenti analoghi

• DRIFT: Harnessing Inherent Fault Tolerance for Efficient and Reliable Diffusion Model Inference
  di: Wen, Jinqi, et al.
  Pubblicazione: (2026)
• The Quest for Reliable AI Accelerators: Cross-Layer Evaluation and Design Optimization
  di: Li, Meng, et al.
  Pubblicazione: (2026)
• Aging Aware Adaptive Voltage Scaling for Reliable and Efficient AI Accelerators
  di: Xie, Tong, et al.
  Pubblicazione: (2026)
• CREATE: Cross-Layer Resilience Characterization and Optimization for Efficient yet Reliable Embodied AI Systems
  di: Xie, Tong, et al.
  Pubblicazione: (2026)
• Efficient yet Accurate End-to-End SC Accelerator Design
  di: Li, Meng, et al.
  Pubblicazione: (2024)