Network and Compiler Optimizations for Efficient Linear Algebra Kernels in Private Transformer Inference

Documenti analoghi

• HE-LRM: Efficient Private Embedding Lookups for Neural Inference Using Fully Homomorphic Encryption
  di: Garimella, Karthik, et al.
  Pubblicazione: (2025)
• DeepReShape: Redesigning Neural Networks for Efficient Private Inference
  di: Jha, Nandan Kumar, et al.
  Pubblicazione: (2023)
• EinHops: Einsum Notation for Expressive Homomorphic Operations on RNS-CKKS Tensors
  di: Garimella, Karthik, et al.
  Pubblicazione: (2025)
• Orion: A Fully Homomorphic Encryption Framework for Deep Learning
  di: Ebel, Austin, et al.
  Pubblicazione: (2023)
• AERO: Entropy-Guided Framework for Private LLM Inference
  di: Jha, Nandan Kumar, et al.
  Pubblicazione: (2024)