When a TF-TRT converted graph with static cuda engines is executed, we call the TensorRT runtime to deserialize cuda engines without initializing the TensorRT plugin registry. This causes TensorRT runtime failure when the cuda engines contain plugins. Move InitializeTrtPlugins to common/utils.cc and replace the use of mutex with absl::call_once. PiperOrigin-RevId: 327679056 Change-Id: I5e50a01aa06f3b5a22a3114a2c54e3712461bd6b |
||
---|---|---|
.. | ||
utils.cc | ||
utils.h |