Chainguard Container for tritonserver-vllm-backend-fips

The Triton Inference Server provides an optimized cloud and edge inferencing solution with vllm backend

Chainguard Containers are regularly-updated, secure-by-default container images.

Download this Container Image

For those with access, this container image is available on cgr.dev:

docker pull cgr.dev/ORGANIZATION/tritonserver-vllm-backend-fips:latest

Be sure to replace the ORGANIZATION placeholder with the name used for your organization's private repository within the Chainguard Registry.

Getting started

The Triton Server with vLLM backend container provides GPU-accelerated large language model inference through NVIDIA's Triton Inference Server with the vLLM backend for optimized performance.

Basic vLLM Model Serving

Set up a simple vLLM model repository and serve the facebook/opt-125m model:

# Create model repository structure
mkdir -p model_repository/vllm_model/1

# Download model configuration
wget -P model_repository/vllm_model/1 https://raw.githubusercontent.com/triton-inference-server/vllm_backend/main/samples/model_repository/vllm_model/1/model.json
wget -P model_repository/vllm_model https://raw.githubusercontent.com/triton-inference-server/vllm_backend/main/samples/model_repository/vllm_model/config.pbtxt

# Start Triton server with vLLM backend
docker run --gpus all -d \
  --name triton-vllm \
  -p 8000:8000 -p 8001:8001 -p 8002:8002 \
  --shm-size=1G --ulimit memlock=-1 --ulimit stack=67108864 \
  -v $(pwd):/workspace -w /workspace \
  cgr.dev/ORGANIZATION/tritonserver-vllm-backend-fips:latest \
  --model-repository ./model_repository

The server will take 2-5 minutes to initialize as it downloads and loads the model.

Health Check and Model Status

Check if the server and model are ready:

# Check server health
curl http://localhost:8000/v2/health/ready

# Check model status
curl http://localhost:8000/v2/models/vllm_model/ready

# Get model metadata
curl http://localhost:8000/v2/models/vllm_model

gRPC Client Inference

Test text generation using the gRPC interface:

# Download sample client and prompts
wget https://raw.githubusercontent.com/triton-inference-server/vllm_backend/main/samples/client.py
wget https://raw.githubusercontent.com/triton-inference-server/vllm_backend/main/samples/prompts.txt

# Run client (requires tritonclient[grpc])
docker run --rm --net=host \
  -v $(pwd):/workspace -w /workspace \
  --entrypoint python3 \
  python:3.12-slim \
  -c "pip install tritonclient[grpc] && python3 client.py -u localhost:8001"

Refer to the vLLM documentation for detailed configuration options.

What are Chainguard Containers?

Chainguard Containers are minimal container images that are secure by default.

In many cases, the Chainguard Containers tagged as :latest contain only an open-source application and its runtime dependencies. These minimal container images typically do not contain a shell or package manager. Chainguard Containers are built with Wolfi, our Linux undistro designed to produce container images that meet the requirements of a more secure software supply chain.

The main features of Chainguard Containers include:

• Minimal design, without unnecessary software bloat
• Daily builds to ensure container images are up-to-date with available security patches
• High quality build-time SBOMs attesting to the provenance of all artifacts within the image
• Verifiable signatures provided by Sigstore
• Reproducible builds with Cosign and apko (read more about reproducibility)

For cases where you need container images with shells and package managers to build or debug, most Chainguard Containers come paired with a -dev variant.

Although the -dev container image variants have similar security features as their more minimal versions, they feature additional software that is typically not necessary in production environments. We recommend using multi-stage builds to leverage the -dev variants, copying application artifacts into a final minimal container that offers a reduced attack surface that won’t allow package installations or logins.

Learn More

To better understand how to work with Chainguard Containers, please visit Chainguard Academy and Chainguard Courses.

In addition to Containers, Chainguard offers VMs and Libraries. Contact Chainguard to access additional products.

Trademarks

This software listing is packaged by Chainguard. The trademarks set forth in this offering are owned by their respective companies, and use of them does not imply any affiliation, sponsorship, or endorsement by such companies.