Containers make apps scalable, but the workflow is broken: Slow to build; Dependencies drift; Registry bloat; Complex Job manifests.
Velda eliminates all these steps, and makes your dev-environment immediately scalable:
- ❌ No Dockerfiles or Manifests
- ❌ No image builds or registries
- ❌ No redeploys on code changes
- ✅ Instant scale from local dev to cloud compute, run in any cloud
Prefix any command with vrun to execute it on cloud resources using the exact same code, data, and dependencies as your development machine.
You may also use vbatch or other commands to orchestrate large scale pipelines.
Velda is designed for:
- ML engineers iterating on training & evaluation
- Data engineers running ad-hoc or scheduled batch jobs
- Infra teams tired of rebuilding containers for every code change
- Deploy Velda cluster.
- Connect to your instance using ssh or Velda CLI and start development.
- Run jobs with
vrun,vbatch
vrun -P gpu-h200-8 python train.py --epochs 100
- Onboard more developers by cloning from an existing templates.
We love contributions from our community ❤️. Pull requests are welcome!
We are super excited for community contributions of all kinds - whether it's code improvements, documentation updates, issue reports, feature requests, or discussions in our Discord.
Join our community here:
Check out velda.io to learn more about Velda and our hosted/enterprise offerings.