[TVM Discuss] [Questions] Relay Level Tiling of Conv2d or any operator

Dear All, I am wondering how can I write a Relay pass that tiles conv2d by the output channels (data partitioning) in Relay graph level? For example, let us assume that I have some relay program like below, and I want to able to traverse the relay graph that contains this conv2d, and able t

[TVM Discuss] [Questions] How to use autotuing after runing the tutorials?

I use these codes to import the .so,json,params files --- [Visit Topic](https://discuss.tvm.ai/t/how-to-use-autotuing-after-runing-the-tutorials/6620/4) to respond. You are receiving this because you en

[TVM Discuss] [Questions] How to use autotuing after runing the tutorials?

yes，i did，and i got this output so I think I made a mistake in import the model which used autotuing. I'm new to ai,I dont know how to import the new module --- [Visit Topic](https://discuss.tvm.ai/t/ho

[TVM Discuss] [Questions] How to use autotuing after runing the tutorials?

Did you uncomment the `tune_and_evaluate` function call in the tutorial? --- [Visit Topic](https://discuss.tvm.ai/t/how-to-use-autotuing-after-runing-the-tutorials/6620/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click

[TVM Discuss] [Questions] How to use autotuing after runing the tutorials?

I have got the .so .paramers and .json,but the module which I use autotuing even slower than the module I didn't use autotuing.Is the way I import it wrong?please help me --- [Visit Topic](https://discuss.tvm.ai/t/how-to-use-autotuing-after-runing-the-tutorials/6620/1) to respond. You a

[TVM Discuss] [Questions] Unbind params from func?

I would like use Relay's built in post-training quantization along with BYOC. Inside the quantize pass params are bound to the main function which causes an issue downstream since I need tensors to be VarNode instead of ConstantNode in BYOC. I think this can be resolved by unbinding params af

[TVM Discuss] [Questions] ROCm 'segmentation fault' error when auto-tuning

Downgrading to xgboost 0.90 fixed the segmentation fault issue! Thanks a lot @t-vi --- [Visit Topic](https://discuss.tvm.ai/t/rocm-segmentation-fault-error-when-auto-tuning/6402/6) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails

[TVM Discuss] [Questions] AttributeError: module 'tvm' has no attribute 'thread_axis'

`thread_axis` is in `tvm.te`. --- [Visit Topic](https://discuss.tvm.ai/t/attributeerror-module-tvm-has-no-attribute-thread-axis/6606/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/u

[TVM Discuss] [Questions] Will TVM be compiled as a standalone C++ library?

Hi, all I'm integrating TVM into a C++ deep learning framework, which is similar to the work of torch-tvm. And during the work, I found that the whole functionality of TVM relies on not only the C++ code, but also the python code, which cannot be compiled into the libtvm.so. For example, th

[TVM Discuss] [Questions] PReLU dimension mismatch error when converting ONNX model to TVM

same problem~ version 0.7_dev nn.prelu(%1, %v336) tensor type `Tensor[(64), float32]` has 1 dimensions, while `Tensor[(64, 1, 1), float32]` has 3 dimensions; unable to unify: `Tensor[(64), float32]` and `Tensor[(64, 1, 1), float32]`; --- [Visit Topic](https://discuss.tvm.ai/t/prelu-dimen