Closed IamMohitM closed 2 years ago
Actually, it seems to be working fine. The issue was that the port of the remote machine was not allowed by the inbound rules on AWS. It works fine by changing the inbound rules.
@IamMohitM Thanks a lot man, your messages really really helped me.
🐛 Describe the bug
I have two models served on a remote server. Accessible via http request without an issue. However, when trying to connect via grpc, I get the error
failed to connect to all address
I have generated the pb2 files using the following command:
The inference.proto and management.proto were downloaded from https://github.com/pytorch/serve/tree/master/frontend/server/src/main/resources/proto
The following is my docker command:
Error logs
The following is my log file
Installation instructions
pip install torchserve torch-model-archiver
Model Packaing
model_1 packaging
model_2 packaging
config.properties
Versions
TorchServe Version is 0.5.3
Repro instructions
python test_scripts/proto/client.py infer model_1 kitten_small.jpg
Possible Solution
No response