Login / Signup

Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference.

Jinghan YaoQuentin AnthonyAamir ShafiHari SubramoniDhabaleswar K. Panda
Published in: CoRR (2024)
Keyphrases
  • probabilistic model
  • multiscale
  • image compression
  • energy function
  • video streams