Commits
  • webgpu qmoe
    guschmue committed 127 days ago
  • Update onnxruntime/contrib_ops/webgpu/moe/swiglu.wgsl.template
    guschmue committed 126 days ago
  • Update onnxruntime/contrib_ops/webgpu/moe/zero_tensor.wgsl.template
    guschmue committed 126 days ago
  • Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
    guschmue committed 126 days ago
  • Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
    guschmue committed 126 days ago
  • Update onnxruntime/contrib_ops/webgpu/moe/hidden_state_gather.wgsl.template
    guschmue committed 126 days ago
  • Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
    guschmue committed 126 days ago
  • Update onnxruntime/contrib_ops/webgpu/moe/qmoe.cc
    guschmue committed 126 days ago
  • fix lint errors
    guschmue committed 126 days ago
  • address review feedback
    guschmue committed 120 days ago
  • address review feedback
    guschmue committed 120 days ago
  • fix chunking of tokens into max_token blocks
    guschmue committed 119 days ago
  • Merge branch 'main' into gs/webgpu-qmoe
    guschmue committed 119 days ago
  • reflect changes in main
    guschmue committed 119 days ago
  • review feedback
    guschmue committed 119 days ago
  • fix build
    guschmue committed 119 days ago
Loading