Starstruk Logo MarkStarstruk

0.1

juanfont/headscale0.1Aug 11, 2023by jafioti

AI Summary

This is the inaugural release of Luminal, a deep learning framework designed for static computation and aggressive optimization. It achieves the first functional milestone, capable of running the full LLaMA 1 7B model to generate valid text, albeit with slow performance.

Key Highlights

  • First functional release of Luminal
  • Support for running LLaMA 1 7B model
  • Generates valid text output
  • Focus on static computation and optimization

New Features

  • LLaMA 1 7B inference
  • Static computation framework
  • Aggressive optimization

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.