brb-nv

Hi, can you please share with us verbose logs of the failing cases with trtexec? `trtexec --onnx= --verbose` Even better if you can share the failing onnx files and parameters...

Sorry, I'm a bit confused what exactly the problem is. - If it's the `malloc_consolidate(): invalid chunk size`, it seems to come from a heap memory management issue [[reference](https://brainly.com/question/43023384)], which...

Can you please share a log where the 7 values are logged and where it is mentioned that it should contain `[min, max, mean, median, 99% percentile]`?

Which release are you working with? Can you try out with our main? If there's still an issue, please share steps to reproduce alongside hardware details.

@lucaslie , do you think you can answer the question about auto deploy?

Hi, are you open to sharing the corresponding onnx file? I tried reproducing the problem with the onnx file from the other [issue](https://forums.developer.nvidia.com/t/tensorrt-conversion-fails-with-dcheck-i-is-use-only/237282) but that onnx file runs smoothly with...

I understand. If you know what part of the network is causing the problem, you could [isolate the subgraph](https://github.com/NVIDIA/TensorRT/tree/master/tools/onnx-graphsurgeon/examples/03_isolating_a_subgraph) and see if that can serve as a minimal example producing...

Hi, I think you have a few options: - Using polygraphy CLI: Example [here](https://github.com/NVIDIA/TensorRT/tree/main/tools/Polygraphy/examples/cli/convert/01_int8_calibration_in_tensorrt) illustrates that you could mention the calibration cache and rebuild the engine without needing to provide...

Above answer explains. But, I'll probably reiterate. From what OP shared, `split` seems to be doing its job - splitting a tensor of shape [1,24953,8,32] along `axis=1` (presumably) into 5...

Thank you for verifying. Kindly provide access to the onnx file.