LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models

Documenti analoghi

• Numerical Error Analysis of Large Language Models
  di: Budzinskiy, Stanislav, et al.
  Pubblicazione: (2025)
• Matrices over a Hilbert space and their low-rank approximation
  di: Budzinskiy, Stanislav
  Pubblicazione: (2025)
• Entrywise tensor-train approximation of large tensors via random embeddings
  di: Budzinskiy, Stanislav
  Pubblicazione: (2024)
• On the distance to low-rank matrices in the maximum norm
  di: Budzinskiy, Stanislav
  Pubblicazione: (2023)
• Quasioptimal alternating projections and their use in low-rank approximation of matrices and tensors
  di: Budzinskiy, Stanislav
  Pubblicazione: (2023)