NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.
Apache License 2.0
722
stars
112
forks
source link
Update merlin-tensorflow image to 23.08 in sagemaker example #1040
This PR updates the sagemaker example to use the latest merlin-tensorflow:23.08 image. Due to changes in triton/systems,
serve file that ships with the triton container is patched and we build our container with this patched version. Specifically, lines 143-167 that were used for disallowing multiple models are removed, and also --model-control-mode=explicit is removed from the last line.
Note also that the training script train.py is updated to reflect the latest changes in the nvtabular workflow.
This PR updates the sagemaker example to use the latest
merlin-tensorflow:23.08
image. Due to changes in triton/systems,serve file that ships with the triton container is patched and we build our container with this patched version. Specifically, lines 143-167 that were used for disallowing multiple models are removed, and also
--model-control-mode=explicit
is removed from the last line.Note also that the training script
train.py
is updated to reflect the latest changes in the nvtabular workflow.