eelbaz/dgx-spark-vllm-setup
One-command vLLM installation for NVIDIA DGX Spark with Blackwell GB10 GPUs (sm_121 architecture)
This project simplifies getting powerful large language models (LLMs) like Qwen or OPT running efficiently on your NVIDIA DGX Spark system equipped with Blackwell GB10 GPUs. It takes care of all the complex software setup, letting you input a model name and get a ready-to-use LLM API or Python environment for generating text or processing language tasks. Researchers, MLOps engineers, or AI developers working on cutting-edge LLM applications on DGX Spark platforms will find this particularly useful.
Use this if you need to quickly and reliably deploy and serve large language models on an NVIDIA DGX Spark server with Blackwell GB10 GPUs for high-performance inference.
Not ideal if you are using different GPU hardware, a non-DGX Spark system, or if you require a highly customized, manual build process from scratch.
Stars
71
Forks
8
Language
Shell
License
MIT
Category
Last pushed
Oct 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/eelbaz/dgx-spark-vllm-setup"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jundot/omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the...
josStorer/RWKV-Runner
A RWKV management and startup tool, full automation, only 8MB. And provides an interface...
jordanhubbard/nanolang
A tiny experimental language designed to be targeted by coding LLMs
waybarrios/vllm-mlx
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models...
akivasolutions/tightwad
Pool your CUDA + ROCm GPUs into one OpenAI-compatible API. Speculative decoding proxy gives you...