VertexC/dl-infer-perf

Issues

• pytorch->tvm cuda oom

  #2 opened 4 years ago by VertexC
  2

• tvm inference performance get worse when batchsize is larger

  #5 opened 4 years ago by VertexC
  1

• onnx->tvm fails on mobilenet/inception/resnet50

  #4 opened 4 years ago by VertexC
  1

• onnx->trt fail on mobilenet

  #3 opened 4 years ago by VertexC
  2

• tf->tvm cuda mobilenet fail

  #1 opened 4 years ago by VertexC
  3