Model Deployment
Three steps are required to deploy the model:
Setup
Prior to deploying a model or pipeline, the model or pipeline must be exported following the steps in Model Export Section. No other additional setup is required as the NeMo container comes with the relevant NVIDIA Triton Inference Server libraries preinstalled and ready to go.
Start NVIDIA Triton Inference Server
Starting the NVIDIA Triton Inference Server is a simple command. First, however, please read the model specific section below to make sure everything is in the correct place. To start the NVIDIA Triton Inference Server:
/opt/tritonserver/bin/tritonserver --log-verbose 2 --model-repository /opt/NeMo-Framework-Launcher/deployment/server --model-control-mode=explicit --load-model neva
File Copy
Copy the generated plan
directory to the deployment/server/neva/1/
directory.
Query NVIDIA Triton Inference Server
In a separate instance of the NeMo container, we can setup a client to query the server. There are a example of the client in deployment/client/neva_client.py
.
At query time, the values, max_new_tokens
, temperature
, random_seed
can be used as optional
inputs. If these are not set, the defaults are the values set during export.
The return is a response from the model
In the client example, make sure to set the prompt and the path to the input image.