Skip to main content
Ctrl+K
AMD Logo
ROCm™ Blogs
  • Home
  • AI
  • HPC
  • Data Science
  • Systems
  • Developers
  • Robotics

ROCm blogs

Posts by Yonatan Dukler

Accelerating Mixture-of-Experts Execution with FarSkip-Collective Models

  • 05 May 2026
  • Yonatan Dukler , Deval Shah , Guihong Li , Vikram Appia , Emad Barsoum
  • English
  • Applications & models
  • AI/ML LLM

Whether you are running training or inference, the largest Mixture-of-Experts (MoE) based LLMs cannot fit on a single GPU; instead you must run collective-communication operations to integrate the work of multiple GPUs to work together on a single model.

Read more ...


  • Terms and Conditions
  • Privacy
  • Trademarks
  • Supply Chain Transparency
  • Fair and Open Competition
  • UK Tax Strategy
  • Cookie Policy
  • Cookie Settings
© 2025 Advanced Micro Devices, Inc