Skip to main content
Ctrl+K
yet-another-onnxruntime-extensions 0.1 documentation - Home yet-another-onnxruntime-extensions 0.1 documentation - Home
  • Getting Started
  • Available Custom Ops
  • Next Steps
  • API Reference
  • Examples
  • GitHub
  • Getting Started
  • Available Custom Ops
  • Next Steps
  • API Reference
  • Examples
  • GitHub

Section Navigation

Discussion

  • Adaptive CUDA expert offloading for Qwen 3.6 MoE
  • Next Steps

Next Steps#

Date:

2026-08

Discussion

  • Adaptive CUDA expert offloading for Qwen 3.6 MoE

previous

Sparse CPU Custom Ops

next

Adaptive CUDA expert offloading for Qwen 3.6 MoE
Show Source

Created using Sphinx 9.1.0.

Built with the PyData Sphinx Theme 0.20.0.