[Bug]: TensorRT 10.x compatibility issues in TensorRTEngineHandlerNumPy

[SaiShashank12]

What happened?

When running Beam’s TensorRT inference handler (TensorRTEngineHandlerNumPy) on TensorRT 10.x, inference fails immediately during initialization:

AttributeError: 'tensorrt.tensorrt.ICudaEngine' object has no attribute 'num_bindings'

This happens because the handler is written against the legacy TensorRT 8.x API. In TensorRT 10, the "bindings" API was removed and replaced with the new tensors API (num_io_tensors, get_tensor_name, get_tensor_mode, execute_async_v3, etc.).

As a result, Beam pipelines cannot run on modern NVIDIA environments using TensorRT 10.x.

Issue Priority

Priority: 2 (default / most bugs should be filed as P2)

Issue Components

• Component: Python SDK
• Component: Java SDK
• Component: Go SDK
• Component: Typescript SDK
• Component: IO connector
• Component: Beam YAML
• Component: Beam examples
• Component: Beam playground
• Component: Beam katas
• Component: Website
• Component: Infrastructure
• Component: Spark Runner
• Component: Flink Runner
• Component: Samza Runner
• Component: Twister2 Runner
• Component: Hazelcast Jet Runner
• Component: Google Cloud Dataflow Runner

[SaiShashank12]

.take-issue

[github-actions]

Label component:ml cannot be managed because it does not exist in the repo. Please check your spelling.

[SaiShashank12]

.take-issue

[SaiShashank12]

This is the docker image that I have used

ARG BUILD_IMAGE=[nvcr.io/nvidia/tensorrt:25.01-py3](http://nvcr.io/nvidia/tensorrt:25.01-py3)
FROM ${BUILD_IMAGE}
ENV PATH="/usr/src/tensorrt/bin:${PATH}"

WORKDIR /workspace

RUN apt-get update -y && \
    apt-get install -y \
    python3-venv \
    libx11-6 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgl1

RUN pip install --no-cache-dir apache-beam[gcp]==2.67.0

COPY --from=apache/beam_python3.10_sdk:2.67.0 /opt/apache/beam /opt/apache/beam


RUN pip install --upgrade pip && \
pip install torch && \
pip install torchvision && \
pip install pillow>=8.0.0 && \
pip install transformers>=4.18.0 && \
pip install cuda-python==12.8 && \
pip install opencv-python==4.7.0.72 && \
pip install PyMuPDF==1.22.5 && \
pip install requests && \
pip install numpy==2.0.1

ENTRYPOINT ["/opt/apache/beam/boot"]

[github-actions]

This issue has been marked as stale due to 150 days of inactivity. It will be closed in 30 days if no further activity occurs. If you think that’s incorrect or this issue still needs to be addressed, please simply write any comment. If closed, you can reopen the issue at any time. Thank you for your contributions.