Apurba Bose
Apurba Bose
LGTM! @HolyWu could you rebase the PR? Pending on CI.
@gs-olive though the test cases pass, I don't think that the decomposition is taking place. It fails in the backend at `aot_export_joint_simple`. Shows me something like ``` CRITICAL:torch_tensorrt.dynamo.backend.backends:Halting compilation on...
Overall looks good to me. Is there any use case for which this lowering pass has been added?
Facing the same issue while running python tools/train.py configs/convnext/convnext-small_upernet_8xb2-amp-160k_ade20k-512x512.py since it requires mmcls with mmcv compatible version mmcv>=1.4.2,
Taking a look at this
Currently the dynamic shapes in the case of split is not supported. I think the issue was when we were trying chunk dynamic shape which led to this https://github.com/pytorch/pytorch/issues/134663 and...
Thanks for the issue. Issue 3177 tracks this
Is this the complete repro code? When I run the above it shows me `TypeError: forward() missing 1 required positional argument: 'L_self_modules_pooler_modules_dense_parameters_bias_'` seems like it is missing some input.