Skip to main content
Tandemn System has two parts: a self-hosted control plane operated by an administrator and a CLI used by the people submitting inference jobs. The current deployment target is AWS.

​
Server requirements

RequirementNotes
Python 3.12+Required for the control plane.
uvRequired for setup and dependency management.
SkyPilotInstalled by setup.sh; run sky check to verify cloud access.
AWS credentialsUse aws configure or ~/.aws/credentials.
AWS IAM permissionsEC2 launch/terminate, S3 read/write to your bucket, and service quota read access.
S3 bucketMust exist in your AWS account and be set as S3_UPLOAD_BUCKET in .env.
RedisRequired for multi-replica chunked jobs.
HuggingFace tokenRequired for gated models such as Llama and Gemma; set HF_TOKEN in .env.
At minimum, AWS credentials need access to the EC2 instance types you plan to use, s3:GetObject and s3:PutObject on your bucket, and servicequotas:GetServiceQuota for quota tracking. Install uv before running server setup: 
curl -LsSf https://astral.sh/uv/install.sh | sh

​
CLI requirements

Users need a Python environment and the URL of the Tandemn server.
  • Python 3.12 or newer
  • pip
  • The tandemn Python package
  • TD_SERVER_URL set to the server URL
pip install tandemn
export TD_SERVER_URL=<your-server-url>
tandemn check
For an initial evaluation, use one administrator-managed server, one CLI user, and a small JSONL workload. Verify connectivity with tandemn check before submitting real workloads.

Install server

Install and start the control plane.

Install CLI

Set up a local CLI environment.