0.1

grokability/snipe-it0.1Aug 11, 2023by jafioti

AI Summary

Luminal 0.1 introduces the first functional version of a deep learning framework designed for static computation and aggressive optimization. The release enables the execution of the full Llama 1 7B model to generate valid text, though performance is currently limited.

Key Highlights

First functional version of the framework
Support for running the full Llama 1 7B model
Focus on static computation and optimization
Valid text generation capability established

New Features

Static computation architecture
Aggressive optimization focus
Llama 1 7B inference support
Valid text generation

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.