Introducing the next evolution in LLM text generation: the first fully-fledged serving system built around a decode megakernel.
Delivering up to 1.58x faster performance than vLLM. Built for North Mini Code, completely open-source.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Gives teams an open-source, faster LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → serving path (up to 1.58x vLLM) built around kernel fusion, with published benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → numbers on H100 hardware.
