NIM¶
This example shows how to deploy LLama 3.1 using NVIDIA NIM and dstack.
Prerequisites
Once dstack is installed, go ahead clone the repo, and run dstack init.
$ git clone https://github.com/dstackai/dstack
$ cd dstack
$ dstack init
Deployment¶
Here's an example of a service that deploys Llama 3.1 8B using vLLM.
type: service
name: llama31
image: nvcr.io/nim/meta/llama-3.1-8b-instruct:latest
env:
- NGC_API_KEY
- NIM_MAX_MODEL_LEN=4096
registry_auth:
username: $oauthtoken
password: ${{ env.NGC_API_KEY }}
port: 8000
# Register the model
model: meta/llama-3.1-8b-instruct
# Uncomment to leverage spot instances
#spot_policy: auto
# Cache downloaded models
volumes:
- /root/.cache/nim:/opt/nim/.cache
resources:
gpu: 24GB
# Uncomment if using multiple GPUs
#shm_size: 24GB
Running a configuration¶
To run a configuration, use the dstack apply command.
$ NGC_API_KEY=...
$ dstack apply -f examples/deployment/nim/.dstack.yml
# BACKEND REGION RESOURCES SPOT PRICE
1 gcp asia-northeast3 4xCPU, 16GB, 1xL4 (24GB) yes $0.17
2 gcp asia-east1 4xCPU, 16GB, 1xL4 (24GB) yes $0.21
3 gcp asia-northeast3 8xCPU, 32GB, 1xL4 (24GB) yes $0.21
Submit the run llama3-nim-task? [y/n]: y
Provisioning...
---> 100%
If no gateway is created, the model will be available via the OpenAI-compatible endpoint
at <dstack server URL>/proxy/models/<project name>/.
$ curl http://127.0.0.1:3000/proxy/models/main/chat/completions \
-X POST \
-H 'Authorization: Bearer <dstack token>' \
-H 'Content-Type: application/json' \
-d '{
"model": "meta/llama3-8b-instruct",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "What is Deep Learning?"
}
],
"max_tokens": 128
}'
When a gateway is configured, the OpenAI-compatible endpoint
is available at https://gateway.<gateway domain>/.
Source code¶
The source-code of this example can be found in
examples/deployment/nim .
Limitations
NIM isn't working yet with runpod and vastai backends.
Track the issue for progress.