SaiShashank12 commented on PR #36309:
URL: https://github.com/apache/beam/pull/36309#issuecomment-3344807843
### Python SDK
#### ML Inference
- Added support for **TensorRT 10.x** with the new
`TensorRTEngineHandlerNumPy`.
This replaces legacy TensorRT < 10 APIs (e.g., `num_bindings`,
`execute_async_v2`)
with the new Tensor API (`num_io_tensors`, `get_tensor_name`,
`execute_async_v3`).
This resolves runtime errors when using TensorRT >= 10 in Beam pipelines.
(See [#36306](https://github.com/apache/beam/issues/36306))
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
