XXX failure of TensorRT 10.1 when running XXX on A10

Description

[08/07/2024-07:27:13] [TRT] [E] IExecutionContext::executeV2: Error Code 3: API Usage Error (Parameter check failed, condition: nullPtrAllowed. Tensor "attention_mask" is bound to nullptr, which is allowed only for an empty input tensor, shape tensor, or an output tensor associated with an IOuputAllocator.)
[08/07/2024-07:27:13] [TRT] [E] [calibrator.cpp::calibrateEngine::1223] Error Code 2: Internal Error (Assertion context->executeV2(bindings.data()) failed. )
Failed building engine

Environment

TensorRT Version:10.1

NVIDIA GPU:A10

NVIDIA Driver Version:535

CUDA Version:12.4

CUDNN Version:

Operating System:

Python Version (if applicable):

Tensorflow Version (if applicable):

PyTorch Version (if applicable):

Baremetal or Container (if so, version):

Relevant Files

Model link:

Steps To Reproduce

Commands or scripts:

Have you tried the latest release?:

Can this model run on other frameworks? For example run ONNX model with ONNXRuntime (polygraphy run <model.onnx> --onnxrt):

The report identifies TensorRT 10.1 on an A10 with CUDA 12.4 and failures at IExecutionContext::executeV2 and calibrator.cpp::calibrateEngine::1223. Start by collecting the missing model, commands, and environment details, then reproduce the engine build and determine why attention_mask is bound to nullptr; done means a confirmed cause and successful build or a documented fix.