Services

Services allow you to deploy models or web apps as secure and scalable endpoints.

Apply a configuration

First, define a service configuration as a YAML file in your project folder. The filename must end with .dstack.yml (e.g. .dstack.yml or dev.dstack.yml are both acceptable).

type: service
name: llama31

# If `image` is not specified, dstack uses its default image
python: "3.11"
env:
  - HF_TOKEN
  - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
  - MAX_MODEL_LEN=4096
commands:
  - pip install vllm
  - vllm serve $MODEL_ID
    --max-model-len $MAX_MODEL_LEN
    --tensor-parallel-size $DSTACK_GPUS_NUM
port: 8000
# (Optional) Register the model
model: meta-llama/Meta-Llama-3.1-8B-Instruct

# Uncomment to leverage spot instances
#spot_policy: auto

resources:
  gpu: 24GB

To run a service, pass the configuration to dstack apply:

$ HF_TOKEN=...
$ dstack apply -f service.dstack.yml

 #  BACKEND  REGION    RESOURCES                    SPOT  PRICE
 1  runpod   CA-MTL-1  18xCPU, 100GB, A5000:24GB:2  yes   $0.22
 2  runpod   EU-SE-1   18xCPU, 100GB, A5000:24GB:2  yes   $0.22
 3  gcp      us-west4  27xCPU, 150GB, A5000:24GB:3  yes   $0.33

Submit the run llama31? [y/n]: y

Provisioning...
---> 100%

Service is published at: 
  http://localhost:3000/proxy/services/main/llama31/
Model meta-llama/Meta-Llama-3.1-8B-Instruct is published at:
  http://localhost:3000/proxy/models/main/

dstack apply automatically provisions instances, uploads the contents of the repo (incl. your local uncommitted changes), and runs the service.

If a gateway is not configured, the service’s endpoint will be accessible at <dstack server URL>/proxy/services/<project name>/<run name>/.

$ curl http://localhost:3000/proxy/services/main/llama31/v1/chat/completions \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer <dstack token>' \
    -d '{
        "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
        "messages": [
            {
                "role": "user",
                "content": "Compose a poem that explains the concept of recursion in programming."
            }
        ]
    }'

If the service defines the model property, the model can be accessed with the global OpenAI-compatible endpoint at <dstack server URL>/proxy/models/<project name>/, or via dstack UI.

If authorization is not disabled, the service endpoint requires the Authorization header with Bearer <dstack token>.

Gateway

Running services for development purposes doesn’t require setting up a gateway.

However, you'll need a gateway in the following cases:

• To use auto-scaling
• To enable HTTPS for the endpoint and map it to your domain
• If your service requires WebSockets
• If your service cannot work with a path prefix

Note, if you're using dstack Sky , a gateway is already pre-configured for you.

If a gateway is configured, the service endpoint will be accessible at https://<run name>.<gateway domain>/.

If the service defines the model property, the model will be available via the global OpenAI-compatible endpoint at https://gateway.<gateway domain>/.

Configuration options

Replicas and scaling

By default, dstack runs a single replica of the service. You can configure the number of replicas as well as the auto-scaling rules.

type: service
# The name is optional, if not specified, generated randomly
name: llama31-service

python: "3.10"

# Required environment variables
env:
  - HF_TOKEN
commands:
  - pip install vllm
  - vllm serve meta-llama/Meta-Llama-3.1-8B-Instruct --max-model-len 4096
# Expose the port of the service
port: 8000

resources:
  # Change to what is required
  gpu: 24GB

# Minimum and maximum number of replicas
replicas: 1..4
scaling:
  # Requests per seconds
  metric: rps
  # Target metric value
  target: 10

The replicas property can be a number or a range.

The metric property of scaling only supports the rps metric (requests per second). In this case dstack adjusts the number of replicas (scales up or down) automatically based on the load.

Setting the minimum number of replicas to 0 allows the service to scale down to zero when there are no requests.

The scaling property currently requires creating a gateway. This requirement is expected to be removed soon.

Model

If the service is running a chat model with an OpenAI-compatible interface, set the model property to make the model accessible via dstack's global OpenAI-compatible endpoint, and also accessible via dstack's UI.

Authorization

By default, the service enables authorization, meaning the service endpoint requires a dstack user token. This can be disabled by setting auth to false.

type: service
# The name is optional, if not specified, generated randomly
name: http-server-service

# Disable authorization
auth: false

python: "3.10"

# Commands of the service
commands:
  - python3 -m http.server
# The port of the service
port: 8000

Path prefix

If your dstack project doesn't have a gateway, services are hosted with the /proxy/services/<project name>/<run name>/ path prefix in the URL. When running web apps, you may need to set some app-specific settings so that browser-side scripts and CSS work correctly with the path prefix.

type: service
name: dash
gateway: false

# Disable authorization
auth: false
# Do not strip the path prefix
strip_prefix: false

env:
  # Configure Dash to work with a path prefix
  # Replace `main` with your dstack project name
  - DASH_ROUTES_PATHNAME_PREFIX=/proxy/services/main/dash/

commands:
  - pip install dash
  # Assuming the Dash app is in your repo at app.py
  - python app.py

port: 8050

By default, dstack strips the prefix before forwarding requests to your service, so to the service it appears as if the prefix isn't there. This allows some apps to work out of the box. If your app doesn't expect the prefix to be stripped, set strip_prefix to false.

If your app cannot be configured to work with a path prefix, you can host it on a dedicated domain name by setting up a gateway.

Resources

If you specify memory size, you can either specify an explicit size (e.g. 24GB) or a range (e.g. 24GB.., or 24GB..80GB, or ..80GB).

type: service
# The name is optional, if not specified, generated randomly
name: llama31-service

python: "3.10"

# Commands of the service
commands:
  - pip install vllm
  - python -m vllm.entrypoints.openai.api_server
    --model mistralai/Mixtral-8X7B-Instruct-v0.1
    --host 0.0.0.0
    --tensor-parallel-size $DSTACK_GPUS_NUM
# Expose the port of the service
port: 8000

resources:
  # 2 GPUs of 80GB
  gpu: 80GB:2

  # Minimum disk size
  disk: 200GB

The gpu property allows specifying not only memory size but also GPU vendor, names and their quantity. Examples: nvidia (one NVIDIA GPU), A100 (one A100), A10G,A100 (either A10G or A100), A100:80GB (one A100 of 80GB), A100:2 (two A100), 24GB..40GB:2 (two GPUs between 24GB and 40GB), A100:40GB:2 (two A100 GPUs of 40GB).

Google Cloud TPU

To use TPUs, specify its architecture via the gpu property.

type: service
name: llama31-service-optimum-tpu

image: dstackai/optimum-tpu:llama31
env:
  - HF_TOKEN
  - MODEL_ID=meta-llama/Meta-Llama-3.1-8B-Instruct
  - MAX_TOTAL_TOKENS=4096
  - MAX_BATCH_PREFILL_TOKENS=4095
commands:
  - text-generation-launcher --port 8000
port: 8000
# Register the model
model: meta-llama/Meta-Llama-3.1-8B-Instruct

resources:
  gpu: v5litepod-4

Currently, only 8 TPU cores can be specified, supporting single TPU device workloads. Multi-TPU support is coming soon.

Shared memory

If you are using parallel communicating processes (e.g., dataloaders in PyTorch), you may need to configure shm_size, e.g. set it to 16GB.

Python version

If you don't specify image, dstack uses its base Docker image pre-configured with python, pip, conda (Miniforge), and essential CUDA drivers. The python property determines which default Docker image is used.

type: service
# The name is optional, if not specified, generated randomly
name: http-server-service    

# If `image` is not specified, dstack uses its base image
python: "3.10"

# Commands of the service
commands:
  - python3 -m http.server
# The port of the service
port: 8000

nvcc

By default, the base Docker image doesn’t include nvcc, which is required for building custom CUDA kernels. If you need nvcc, set the corresponding property to true.

type: service
# The name is optional, if not specified, generated randomly
name: http-server-service    

# If `image` is not specified, dstack uses its base image
python: "3.10"
# Ensure nvcc is installed (req. for Flash Attention) 
nvcc: true

 # Commands of the service
commands:
  - python3 -m http.server
# The port of the service
port: 8000

Docker

If you want, you can specify your own Docker image via image.

type: service
# The name is optional, if not specified, generated randomly
name: http-server-service

# Any custom Docker image
image: dstackai/base:py3.13-0.7-cuda-12.1

# Commands of the service
commands:
  - python3 -m http.server
# The port of the service
port: 8000

Private registry

Use the registry_auth property to provide credentials for a private Docker registry.

type: service
# The name is optional, if not specified, generated randomly
name: http-server-service

# Any private Docker iamge
image: dstackai/base:py3.13-0.7-cuda-12.1
# Credentials of the private registry
registry_auth:
  username: peterschmidt85
  password: ghp_e49HcZ9oYwBzUbcSk2080gXZOU2hiT9AeSR5

# Commands of the service  
commands:
  - python3 -m http.server
# The port of the service
port: 8000

Privileged mode

All backends except runpod, vastai, and kubernetes support running containers in privileged mode. This mode enables features like using Docker and Docker Compose inside dstack runs.

Environment variables

type: service
# The name is optional, if not specified, generated randomly
name: llama-2-7b-service

python: "3.10"

# Environment variables
env:
  - HF_TOKEN
  - MODEL=NousResearch/Llama-2-7b-chat-hf
# Commands of the service
commands:
  - pip install vllm
  - python -m vllm.entrypoints.openai.api_server --model $MODEL --port 8000
# The port of the service
port: 8000

resources:
  # Required GPU vRAM
  gpu: 24GB

If you don't assign a value to an environment variable (see HF_TOKEN above), dstack will require the value to be passed via the CLI or set in the current process.

System environment variables

The following environment variables are available in any run by default:

Name	Description
DSTACK_RUN_NAME	The name of the run
DSTACK_REPO_ID	The ID of the repo
DSTACK_GPUS_NUM	The total number of GPUs in the run

Spot policy

By default, dstack uses on-demand instances. However, you can change that via the spot_policy property. It accepts spot, on-demand, and auto.

Reference

Services support many more configuration options, incl. backends, regions, max_price, and among others.

Retry policy

By default, if dstack can't find capacity, the task exits with an error, or the instance is interrupted, the run will fail.

If you'd like dstack to automatically retry, configure the retry property accordingly:

Creation policy

By default, when you run dstack apply with a dev environment, task, or service, if no idle instances from the available fleets meet the requirements, dstack creates a new fleet using configured backends.

To ensure dstack apply doesn't create a new fleet but reuses an existing one, pass -R (or --reuse) to dstack apply.

$ dstack apply -R -f examples/.dstack.yml

Or, set creation_policy to reuse in the run configuration.

Idle duration

If a fleet is created automatically, it stays idle for 5 minutes by default and can be reused within that time. If the fleet is not reused within this period, it is automatically terminated. To change the default idle duration, set idle_duration in the run configuration (e.g., 0s, 1m, or off for unlimited).

Fleets

For greater control over fleet provisioning, it is recommended to create fleets explicitly.

Manage runs

dstack provides several commands to manage runs:

• dstack ps – Lists all running jobs and their statuses. Use --watch (or -w) to monitor the live status of runs.
• dstack stop – Stops a run gracefully. Pass --abort or -x to stop it immediately without waiting for a graceful shutdown. By default, a run runs until you stop it or its lifetime exceeds the value of max_duration.
• dstack attach – By default, dstack apply runs in attached mode, establishing an SSH tunnel to the run, forwarding ports, and displaying real-time logs. If you detach from a run, use this command to reattach.
• dstack logs – Displays run logs. Pass --diagnose or -d to view diagnostic logs, which can help troubleshoot failed runs.

What's next?

1. Read about dev environments, tasks, and repos
2. Learn how to manage fleets
3. See how to set up gateways
4. Check the TGI , vLLM , and NIM examples