0.1

ChatGPTNextWeb/NextChat0.1Aug 11, 2023by jafioti

AI Summary

This is the initial release of Luminal, a deep learning framework focused on static computation and aggressive optimization, capable of running Llama 1 7B models.

Key Highlights

  • Initial functional version of the framework
  • Support for Llama 1 7B model inference
  • Focus on static computation and optimization
  • Capable of generating valid text (though slow)

New Features

  • Static computation framework
  • Llama 1 7B inference support
  • Aggressive optimization focus

Full Release Notes

This is the first release of luminal, a deep learning framework focused on static computation and aggressive optimization.

This release marks the first functional version. Currently examples/llama can run the full llama 1 7B and generate valid text, though it runs very slow.

Future work will speed this up significantly.