GPU Compute
Run or serve GPU workloads from one command
Badgr supports many GPU workloads through two commands: badgr serve for persistent endpoints, badgr run for jobs. You don't configure compute providers. You run commands.
1. Install and log in
npm install -g badgr-cli
Requires Node.js 18+. Installs the badgr command.
badgr login
Prompts for your API key and saves it to ~/.badgr/config.json.
2. Two commands, everything else is a recipe
badgr serve <model>Start a persistent OpenAI-compatible endpoint. Stays running until you run badgr down.badgr run <command>Run a one-off GPU job. Streams logs, exits when done. Billing stops automatically.badgr down <id>Terminate any deployment. Stops billing immediately.badgr logs <id>Fetch log output from a running or completed deployment.badgr receiptsCost, route, and retry record for every action.3. What you can build
badgr serve— persistent endpoints
LLaMA, Mistral, Qwen, and any Hugging Face model via vLLM
Custom vLLM config, version pinning, extended context
Run TEI or a vLLM embedding model as a persistent API
Serve a Diffusers or ComfyUI container as an endpoint
Persistent Whisper endpoint for audio-to-text workloads
badgr run— jobs that start, run, and exit
Run any Python script or container command on a GPU
Offline scoring, embedding generation, large-scale eval
Adapter training with Axolotl, TRL, or custom scripts
Diffusers, ComfyUI, or video synthesis pipelines
Whisper batch jobs, audio processing pipelines
Integrations
badgr-run and badgr-serve composite actions for CI/CD pipelines
badgr-mcp exposes GPU tools to Claude, Cursor, and other coding agents
4. Quick examples
Serve a model
badgr serve meta-llama/Llama-3.1-8B-Instruct
Run a job
badgr run python train.py --gpu A100
Stop billing
badgr down <deployment-id>
GPU options
Badgr Auto selects the best eligible GPU for your workload. Use --gpu or --min-vram only when you need more control.
RTX_3090NVIDIA RTX 309024 GBRTX_4090NVIDIA RTX 409024 GBL40SNVIDIA L40S48 GBA100NVIDIA A10040–80 GBH100NVIDIA H10080 GBAvailable GPU types may vary by region and current capacity. Run badgr capacity or use --dry-run to confirm availability and pricing before provisioning.