[Apache TVM Discuss] [Questions] Now that we have autoTVM, Why we need topi?

I guess you've used RandomTuner or GridTuner, which traverses the whole search space randomly or in sequence. As for the ML part of the AutoTVM, it means to use the XGBTuner in the current code base. With which, AutoTVM extracts features from a given schedule and uses a XGBoost model to predi

[Apache TVM Discuss] [Questions] Is there any support for auto tuning symbolic shape operations?

Yeah. We didn't do auto tuning on symbolic shape yet, but scheduling symbolic shape operators is well supported --- [Visit Topic](https://discuss.tvm.apache.org/t/is-there-any-support-for-auto-tuning-symbolic-shape-operations/7889/5) to respond. You are receiving this because you enabled

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

Sorry, I send you the loading model part code into TVM. Our code can not be uploaded in the git repo. You only run this 'import_rnnt.py' , and it will reproduce the error. It needs a 'rnnt.toml' which is in the same path. You need to download the rnnt checkpoint by pytorch. https://zenodo.org/r

[Apache TVM Discuss] [Questions] Is there any support for auto tuning symbolic shape operations?

I find "te.var" could solve my problem. Thanks a lot! --- [Visit Topic](https://discuss.tvm.apache.org/t/is-there-any-support-for-auto-tuning-symbolic-shape-operations/7889/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [cli

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

sorry can you make a git repo with all necessary files? --- [Visit Topic](https://discuss.tvm.apache.org/t/import-rnn-t-pytorch-model-into-tvm/7874/12) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discus

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

There are some other files "helpers.py", "metrics.py", "preprocessing.py", "dataset.py" helpers.py: ``` # Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved. # Copyright (c) 2019, Myrtle Software Limited. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "Lic

[Apache TVM Discuss] [Questions] Is there any support for auto tuning symbolic shape operations?

Thanks for answering! By the way, can we schedule operations with variable tensor shapes as we can do with static tensor shapes? Say, bind or split a given axis at certain stage. I am trying to set up scheduling process by hand written scheduling template, but I cannot figure out how to perfor

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

The model of RNNT is from https://zenodo.org/record/3662521 --- [Visit Topic](https://discuss.tvm.apache.org/t/import-rnn-t-pytorch-model-into-tvm/7874/10) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://di

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

Hi, I copy and paste 4 script. The RNN is defined in 'rnn.py'. The rnnt is defined in 'model_rnnt.py'. I tried to import the rnnt model into TVM . Please check it in first script. In the function get_rnnt_model I load the pre-trained model RNNT. In the function rnnt_model_to_tvm_mod , I tried to

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

rnn.py ``` # Copyright (c) 2019, Myrtle Software Limited. All rights reserved. # Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a c

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

decoders.py ``` # Copyright (c) 2019, Myrtle Software Limited. All rights reserved. # Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtai

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

model_rnnt.py ``` # Copyright (c) 2019, Myrtle Software Limited. All rights reserved. # Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obt

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

``` # Licensed to the Apache Software Foundation (ASF) under one # or more contributor license agreements. See the NOTICE file # distributed with this work for additional information # regarding copyright ownership. The ASF licenses this file # to you under the Apache License, Version 2.0 (the

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

can you show me your script so that I can reproduce your problem? --- [Visit Topic](https://discuss.tvm.apache.org/t/import-rnn-t-pytorch-model-into-tvm/7874/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https

[Apache TVM Discuss] [Questions] Import RNN-T pytorch model into TVM

Also, I use torch.jit.trace. But, There are ‘aten::lstm', 'aten::copy_' are not supported. ``` Traceback (most recent call last): File "/Automation/zzhen/pycharm-community-2019.3.3/plugins/python-ce/helpers/pydev/pydevd.py", line 1434, in _exec pydev_imports.execfile(file, globals, local

[Apache TVM Discuss] [Questions] Is there any support for auto tuning symbolic shape operations?

No it’s not supported yet at least in the upstream. Although we’ve been talking this for a while, we haven’t really got a chance to make a concrete plan. --- [Visit Topic](https://discuss.tvm.apache.org/t/is-there-any-support-for-auto-tuning-symbolic-shape-operations/7889/2) to respond.