[TVM Discuss] [Questions] Binding two IterVars in one loop nest to the same thread

TE allows multiple IterVars on one attaching path (i.e. two nested loops) binding to one thread IterVar. It seems necessary for some schedules that model stages having different thread allocation to have correct bounds to be inferred. These schedules certainly represent valid and useful use

[TVM Discuss] [Questions] Problems when import BERT model from PyTorch Relay

Sorry I didn't make it clear. The code pasted in the first issue works well after adopting your solution. Then I tested 'gpt2' model, it reported an error: ``` TypeError: int() argument must be a string, a bytes-like object or a number, not ‘Call’ ``` The test code is shown below: ``` from tvm

[TVM Discuss] [Questions] [Solved] Schedule not registered for 'mytarget'

I finally figured it out. It was because I didn't specify "keys" when I create the new 'mytarget'. Once I add 'mytarget' as the key, the dense_strategy registration works like a charm... It is really appreciated there'll be a tutorial/docs on how to add a new target, :slight_smile: --- [

[TVM Discuss] [Application] Example of a model using attention?

I think that will be very useful, thank you --- [Visit Topic](https://discuss.tvm.ai/t/example-of-a-model-using-attention/6687/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubsc

[TVM Discuss] [Questions] Schedule not registered for 'mytarget'

@hht, I doubled checked, it seems the real problem might be that I declared 'mytarget' as a completely new target, instead of declaring it as a device under target 'ext_dev'. Running ``` print(tvm.target.Target.current(allow_none=False) ``` Shows different result. With VTA: ``` relay/backe

[TVM Discuss] [Application] Example of a model using attention?

I think there is an example in PyTorch: https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html Hope this could help :-) --- [Visit Topic](https://discuss.tvm.ai/t/example-of-a-model-using-attention/6687/2) to respond. You are receiving this because you enabled mail

[TVM Discuss] [Application] Example of a model using attention?

My research collaborators are interested in porting some RNNs with attention into Relay. Are there existing public examples of Relay models that use attention that I could use as a guide to implement some of these RNNs? I would appreciate any examples or assistance --- [Visit Topic](http

[TVM Discuss] [Questions] Problems when import BERT model from PyTorch Relay

> from tvm import relay > import torch > from pytorch_pretrained_bert import BertTokenizer, BertModel, BertForMaskedLM > import logging > > logging.basicConfig(level=logging.INFO) I used the code you pasted in the first issue and its able to generate complete relay function. Im not able to ge

[TVM Discuss] [Questions] Problems when import BERT model from PyTorch Relay

Thanks! I try to fix it by ``` def _tensortonum(): def _impl(inputs, input_types): return inputs[0] return _impl ``` Another error accurs: ``` TypeError: int() argument must be a string, a bytes-like object or a number, not 'Call' ``` ``` '58', %58 : Scalar = prim::ImplicitTe

[TVM Discuss] [Questions] Problems when import BERT model from PyTorch Relay

[PR 5603](https://github.com/apache/incubator-tvm/pull/5603) will help to solve the issue of `prim::ImplicitTensorToNum` If you come across issue with matmul, you can merge [PR 5604](https://github.com/apache/incubator-tvm/pull/5604) as well. --- [Visit Topic](https://discuss.tvm.ai/t/pr

[TVM Discuss] [Questions] Issue with static tensor array

I dont think its fixed yet i am having same issues so any update regarding this --- [Visit Topic](https://discuss.tvm.ai/t/issue-with-static-tensor-array/6333/8) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](