Logo
  • Resource Overview
  • Apply for access and computational resources
  • Onboarding guide
  • Access
  • Accounting
  • Running jobs
  • Optimisaion guides
    • AMD Zen2 Optimization Guide (Discoverer CPU partition)
    • Intel Sapphire Rapids Optimisation Guide (Discoverer+ GPU partition)
    • Unified memory on DGX H200 with Sapphire Rapids: optimisation, optimal use, and programming models
    • Serving Kimi K2.5 on DGX H200 with vLLM and SLURM
    • Serving Kimi K2.6 on DGX H200 with vLLM and SLURM
    • Running Kimi K2.5+ across two DGX H200 nodes on Discoverer+
    • Serving Mixtral 8x7B and 8x22B on DGX H200 with vLLM and SLURM
  • Compatibility guides
  • Where and how to compile code
  • Data transfer
  • ML/AI on Discoverer
  • Storage
  • Software
  • SSH Security
  • Setting your time zone
  • Acknowledgements
  • Getting help
Discoverer HPC Docs
  • Optimisaion guides
  • View page source

Optimisaion guides

Contents:

  • AMD Zen2 Optimization Guide (Discoverer CPU partition)
  • Intel Sapphire Rapids Optimisation Guide (Discoverer+ GPU partition)
  • Unified memory on DGX H200 with Sapphire Rapids: optimisation, optimal use, and programming models
  • Serving Kimi K2.5 on DGX H200 with vLLM and SLURM
  • Serving Kimi K2.6 on DGX H200 with vLLM and SLURM
  • Running Kimi K2.5+ across two DGX H200 nodes on Discoverer+
  • Serving Mixtral 8x7B and 8x22B on DGX H200 with vLLM and SLURM
Previous Next

© Copyright 2026, Discoverer HPC.

Built with Sphinx using a theme provided by Read the Docs.