Eikan Wang

```c++ torch::Tensor feats =torch::zeros({1, num_frames, feature_dim}, torch::kFloat); ``` The input tensor 3-dims. It cannot be converted to `torch.channels-last` because `torch.channels-last` serves for 4-dims tensor - `nchw`.

In general, IPEX could boost a broad set of workloads. And the performance improvement is significant on the top of JIT graph if the model could be traced as a...

Your comment is appreciated. We will have an internal discussion first and keep you posted. Seems like we need to build a more elegant exception capture mechanism.

@abhilash1910 , the `sample_input` is used to query the optimal memory layout for performance. And IPEX has exposed this API. @zhuhaozhe , could you please check the root cause?

@XiaobingSuper, have you encountered this issue?

From PyTorch 1.10 and extension 1.10, we will change the package name to the intel_extension_for_pytorch per legal's requirement and change the underlying device from XPU to CPU. It means that...

@ashahba , will you submit a PR to IPEX 1.12 release branch to address this issue?

@yangw1234 , we released the latest IPEX to fix the issue. Could you please try the latest IPEX and check whether the issue has been fixed?

https://pypi.org/project/intel-extension-for-pytorch/1.12.100/

@ZolotukhinM, Since we add more fusions by leveraging `ExternalCall`, this PR is more critical to Conv post-op fusions.