[GitHub] [incubator-mxnet] QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization

QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-615882613 @mk-61 Thank you for your proposal. Generating a unique key based on model an inference attributes

[GitHub] [incubator-mxnet] QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization

QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-615882613 @mk-61 Thank you for your proposal. Generating a unique key based on model an inference attributes

[GitHub] [incubator-mxnet] QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization

QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-537932809 Thank you for the feedback @KellenSunderland. I think the mini-batchsize should be included as a

[GitHub] [incubator-mxnet] QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization

QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-537934625 Regarding the export of a TensorRT executor handle (@Caenorst, @haohuanw), the [ONNX-TensorRT

[GitHub] [incubator-mxnet] QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization

QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-537932809 Thank you for the feedback @KellenSunderland. I think the mini-batchsize should be included as a

[GitHub] [incubator-mxnet] QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization

QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-537934625 Regarding the export of a TensorRT executor handle (@Caenorst), the [ONNX-TensorRT

[GitHub] [incubator-mxnet] QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization

QueensGambit edited a comment on issue #16173: Saving and loading cudNN autotune and graph optimization URL: https://github.com/apache/incubator-mxnet/issues/16173#issuecomment-537932809 Thank you for the feedback @KellenSunderland. I think the mini-batchsize should be included as a