D-com: Accelerating Iterative Processing to Enable Low-rank Decomposition of Activations

Documenti analoghi

• FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI
  di: Tahmasebi, Faraz, et al.
  Pubblicazione: (2024)
• Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads
  di: Karami, Rachid, et al.
  Pubblicazione: (2024)
• DEEP-GAP: Deep-learning Evaluation of Execution Parallelism in GPU Architectural Performance
  di: Palaniappan, Kathiravan
  Pubblicazione: (2026)
• Fast NF4 Dequantization Kernels for Large Language Model Inference
  di: Qi, Xiangbo, et al.
  Pubblicazione: (2026)
• Design Space Exploration of Approximate Computing Techniques with a Reinforcement Learning Approach
  di: Saeedi, Sepide, et al.
  Pubblicazione: (2023)