Open RZachLamberty opened 3 years ago
Hi @RZachLamberty , I stumbled upon your issue here. I was trying to create a custom docker image and had a similar issue. Installing multi-model-server
(pip install multi-model-server
) did away with this issue. You can give it a try :)
Describe the bug
sagemaker-inference
recently (10/15) released v1.5.3, which included this commit updating the name of the model server artifact and command frommxnet-model-server
tomulti-model-server
.all containers defined in this repository install
sagemaker-inference
as a dependency of this repo itself, on linesand this repo's
setup.py
has aninstall_requires
which includessagemaker-inference>=1.3.1
. as a result,sagemaker-inference=1.5.3
installed.so while the
Dockerfile
'sCMD
value (which callsmxnet-model-server
directly) will succeed, attempts to use theENTRYPOINT
withserve
as a build arg will fail with message:To reproduce
inference.py
(e.g.half_plus_three
) into/opt/ml/model
docker run [tag name] serve
Expected behavior tensorflow serving serves the mounted model /
inference.py
System information A description of your system. Please provide: