← Back to match
DGX Spark Inference Stack
Docker-based LLM inference stack for running local models on an NVIDIA DGX Spark
PlatformWebfreeglobal
DGX Spark Inference Stack is a Docker-based LLM inference stack built primarily around vLLM with intelligent resource management, designed to run on an NVIDIA DGX Spark desktop AI supercomputer. It's aimed at DGX Spark owners who want a ready-to-run local LLM serving setup rather than assembling their own inference stack from scratch.
Categories
AI infrastructurelocal LLM tooling

