Skip to main content
Tandemn is operated by users through the CLI. Start by checking connectivity, then submit jobs with tandemn deploy.

CLI overview

Install, configure, and use the Tandemn CLI.

tandemn check

Verify that your CLI can reach the Tandemn server.

tandemn deploy

Plan or submit a model inference job with a JSONL input file.

Replica operations

Add, kill, or hot-swap replicas while a job is running.

Monitoring

Watch progress, metrics, logs, clusters, and the web dashboard.

Analytics

Inspect completed runs, per-replica summaries, and scheduler timeseries.

Input format

Prepare OpenAI-style batch JSONL workloads.

​
Minimal workflow

pip install tandemn
export TD_SERVER_URL=<your-server-url>
tandemn check
tandemn plan Qwen/Qwen2.5-7B-Instruct prompts.jsonl --slo 4
tandemn deploy Qwen/Qwen2.5-7B-Instruct prompts.jsonl --slo 4
tandemn progress

CLI overview

The Tandemn System command line workflow.

tandemn check

Verify that the Tandemn CLI can reach the server.

plan and deploy

Preview placement plans and submit inference jobs to Tandemn System.

Replica operations

Add, kill, and hot-swap Tandemn replica clusters.

Monitoring and operations

Monitor Tandemn jobs, metrics, clusters, logs, and cleanup.

Analytics

Inspect completed Tandemn runs and scheduler timeseries.

Input format

Prepare OpenAI-style batch JSONL workloads for Tandemn System.