Patrick Liu

hey @cehongwang @narendasan was this ever resolved? what was the issue? im seeing nan values as well for my network. thanks!

@narendasan can you point me to what resolved the issue? im still seeing this for my network after taking changes from HEAD of main

cc @narendasan @peri044 maybe? 🙏

hey @peri044 , thanks for the response. i tried modelopt -> export on a simple model below. am i using this wrong or missing something obvious? im using non-strict export...

hey @lanluo-nvidia thanks for checking! here are my pytorch and modelopt versions: ``` nvidia-modelopt 0.29.0 nvidia-modelopt-core 0.29.0 torch 2.5.1 ```

thanks @lanluo-nvidia - upgrading to torch 2.6 resolves the issue. compiling the exported program gives me something unexpected though. for reference, the model (after `mtq.quantize()`) is: ``` JustAConv( (conv): QuantConv2d(...

thanks so much @lanluo-nvidia !

yea let me get one

@narendasan @apbose this is a stripped down portion of Meta's SAM2 (original at https://github.com/facebookresearch/segment-anything-2/blob/main/sam2/modeling/sam/prompt_encoder.py), with minor modifications of `_embed_points` fill in `CHECKPOINT_PATH` and run the below `python ...` ```python #...

you should see this fx Graph dump as part of the stack trace ``` While executing %cat_5 : [num_users=1] = call_function[target=torch.ops.aten.cat.default](args = ([%_frozen_param0, %where_3], 1), kwargs = {_itensor_to_tensor_meta: {: ((1,...