microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
14.77k stars 2.94k forks source link

[TensorRT EP Plugin] Add cuda::Impl_Cast #22908

Closed chilo-ms closed 1 day ago

chilo-ms commented 1 day ago

TRT 8 doesn't support INT64 and DOUBLE data type. TRT 10 doesn't support DOUBLE data type.

Therefore, TRT EP internally needs to convert INT64 to INT32, and DOUBLE to FLOAT, which needs the cuda::Impl_Cast function. The implementation is copied from CUDA EP.