TensorRT saved model too large to use with TFServing
bharatv007 opened this issue · 4 comments
bharatv007 commented
Versions:
Tensorflow- 2.3.0-rc1
CUDA-10
TensorRT-6
I am trying to convert a GPT2 model, the saved model size is about 1.9GB. It causes an issue when I try to use TF serving for deployment as it hits a protobuf limit of 1 GB. I have tried to not build TRT engines before deployement too, but it did not affect the size of the saved_model.pb.
ericxsun commented
I met the same problem on tf-2.4.1
forrest0402 commented
I also met this problem