# \`serving\` signature in TensorFlow Serving blogpost
**URL:**
**Author:**  [@christopher](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fchristopher)%5C
**Post date:** [August 5, 2021, 6:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fserving-signature-in-tensorflow-serving-blogpost%2F9005%2F1 "2021-08-05T18:02:04Z")
Hi everyone!
I am currently working through @jplu 's [blogpost](https://huggingface.co/blog/tf-serving) on serving a HuggingFace model with TF-Serving, in which he overwrites the model’s `serving` method to change the signature of the traced graph input to accept embeddings.
That, in turn, led me to discover that this `serving` signature is part of all TF models ([Models — transformers 4.7.0 documentation](https://huggingface.co/transformers/main_classes/model.html#transformers.TFPreTrainedModel.serving))
Can someone explain to me how exactly this `serving` method is used by the model server? I can’t find it referenced in the rest of the tutorial and I wasn’t succesful in finding my way around the codebase.
Is that redefined signature used at all in the tutorial? I might be mistaken, but it seems to me that the requests (both REST and gRPC) to the TF-server use the output of the tokenizer, not those of an embedding layer.
---
**Author:**  [@lewtun](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flewtun)%5C
**Post date:** [August 5, 2021, 8:03pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fserving-signature-in-tensorflow-serving-blogpost%2F9005%2F2 "2021-08-05T20:03:19Z")
cc @Rocketknight1
---
**Author:**  [@christopher](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fchristopher)%5C
**Post date:** [August 9, 2021, 8:17am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fserving-signature-in-tensorflow-serving-blogpost%2F9005%2F3 "2021-08-09T08:17:55Z")
I missed the fact that the `serving` method is explicitly exported as a metagraph in the SavedModel for all TF models ([see here](https://github.com/huggingface/transformers/blob/3ff2cde5ca4a2d3c622b827d9edf7e3d0b7f4fb7/src/transformers/modeling_tf_utils.py#L1078))
EDIT:
One thing that’s still not completely clear to me are the redefined inputs. The tutorial changes the `serving` method to accept token embeddings, yet the requests to the model use the output of the tokenizer, so token ids. What am I not seeing?