Home Projects dgx-spark-inference-stack
dgx-spark-inference-stack

dgx-spark-inference-stack

by jdaln · GitHub

Serve the home! Inference stack for your Nvidia DGX Spark aka the Grace Blackwell AI supercomputer on your desk. Mostly vLLM based for now and single-spark. For the not-so-rich buddies. If you want latest/in-testing, look at the branches

# cuda# dgx# dgx-spark# docker
View on GitHub
⭐ Stars
50
🍴 Forks
5
🔥 Trending
+1 today
📜 License
Apache-2.0
Commercial use OK
📅 Created
2026
🔄 Last commit
8 days ago
🏷️ Category
cuda
💻 Language
🖥️ Self-hostable
Likely
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
dgx-spark-inference-stack — GitHub preview card
📈 Star history
5049
2026-07-202026-07-21
📄 About

Serve the home! Inference stack for your Nvidia DGX Spark aka the Grace Blackwell AI supercomputer on your desk. Mostly vLLM based for now and single-spark. For the not-so-rich buddies. If you want latest/in-testing, look at the branches

Frequently asked questions

What is dgx-spark-inference-stack?

Serve the home! Inference stack for your Nvidia DGX Spark aka the Grace Blackwell AI supercomputer on your desk. Mostly vLLM based for now and single-spark. For the not-so-rich buddies. If you want latest/in-testing, look at the branches

Is dgx-spark-inference-stack open source?

dgx-spark-inference-stack is an open-source project. It is released under the Apache-2.0 license.

Is dgx-spark-inference-stack free?

Yes. dgx-spark-inference-stack is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?
OpenSourceAI badge — dgx-spark-inference-stack

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![OpenSourceAI](https://opensourceai.tech/badge.php?tool=jdaln-dgx-spark-inference-stack)](https://opensourceai.tech/project/jdaln-dgx-spark-inference-stack.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.