Chao Zhang

Results 63 comments of Chao Zhang

🐛 [Bug] Returning list of tensors fails when operations are applied to tensors: `RuntimeError: [Error thrown at core/conversion/conversion.cpp:220] List type. Only a single tensor or a TensorList type is supported.`

May be due to #428

🐛 [Bug] Returning list of tensors fails when operations are applied to tensors: `RuntimeError: [Error thrown at core/conversion/conversion.cpp:220] List type. Only a single tensor or a TensorList type is supported.`

> Ah, I think I understand what is happening. In the cases of append and similar cases where PyTorch operates on groupings of Tensors which are already converted, we use...

🐛 [Bug] Segmentation Fault When Trying to Quantize ResNet50 model

Might be related to #898? @henrycharlesworth Can you try building and running Torch-TensorRT with the TensorRT NGC containers? I was able to bypass my issue using `nvcr.io/nvidia/tensorrt:22.02-py3`, PyTorch 1.10, and...

✨[Feature] Support `list` and `namedtuple` input types to `forward` function

@narendasan Let me know if the behaviors listed under **Additional context** make sense. In particular, I believe we currently ignore other input types going into `forward`... if we allow them...

✨[Feature] Support `list` and `namedtuple` input types to `forward` function

Ah this might be a duplicate of #428, although this request might be slightly less ambitious.

✨[Feature] Support `list` and `namedtuple` input types to `forward` function

Sounds good, I'll take a look at the design doc and make some suggestions there for review. I had a quick look at the code and my naive first pass...

✨[Feature] Support `list` and `namedtuple` input types to `forward` function

Yeah that makes sense. I'll take a look at this shortly.

✨[Feature] Support `list` and `namedtuple` input types to `forward` function

Deferring to @inocsin in #629 here

🐛 [Bug] Compilation causes error: `RuntimeError: [Error thrown at core/partitioning/shape_analysis.cpp:66] Expected ivalues_maps.count(input) to be true but got false Could not find torch::jit::Value* 47 produced from %47 : int = prim::dtype(%52) in lowering graph for mini graph input.`

This looks similar to issue #756, with fix #757. Looking at the sources, it looks like this fix may not have made it into `/release/ngc/22.02` but should be present in...

🐛 [Bug] Compilation causes error: `RuntimeError: [Error thrown at core/partitioning/shape_analysis.cpp:66] Expected ivalues_maps.count(input) to be true but got false Could not find torch::jit::Value* 47 produced from %47 : int = prim::dtype(%52) in lowering graph for mini graph input.`

Just tried fix #757 with master commit `11bcb98d3cd680c3c34e6cc4c4efdc7512c144cc` built in NGC container `nvcr.io/nvidia/tensorrt:22.02-py3` and PyTorch 1.10, and the error persists, so it's likely that #757 does not address this issue.