megakernels

Here is 1 public repository matching this topic...

The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.

aws inference glm neuron nki openai-api llm llm-serving trainium megakernels

To associate your repository with the megakernels topic, visit your repo's landing page and select "manage topics."