nrothGIT

TensorRT rebuilds ops at run time

34

At run time, I call `converter.convert() converter.build(input_fn = some_input_fn) converter.save()` ` And see logging to the effect of ``` tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: StatefulPartitionedCall/model_1/TRTEngineOp_1_native_segment 2020-03-18 01:30:00.932297: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]...

## 📚 Documentation I believe the optimizer in this example should be declared after the parallelize module call, as in sequence parallelism. Without this, in latest torch, the example seems...