NVIDIA /
spark-local-inference
Updated 46 min ago
+70 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
It needs a Blackwell-class NVIDIA SM120 or SM121 GPU, such as DGX Spark, plus PyTorch, FlashInfer, and a Rust toolchain. It is a research prototype and a local inference server for long conversations and coding agents.
Summary written by AI from the repository’s description and README.
NVIDIA / spark-local-inference
View on GitHub(opens in new tab)