Lucebox inference engine for heterogeneous hardware & consumer GPUs
Repository Index
64,764 visible repositories in the index
1–3 of 3 · Most stars
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
reproducing the flapping airplanes megakernel, in collab with magni