#gpu

2 pages search “gpu” ↳ all tags

Wiki 1

  • GLM5.2 on AMD MI355X Wafer's vendor benchmark claiming 2626 tok/s/node for GLM5.2 on MI355X, and how they got there

Toolbox 1

  • local-llm (jamesob) Build guide and configs for a 4x RTX PRO 6000 local inference rig, including PCIe switch tuning