Starstruk Logo MarkStarstruk

0.2

ruixenui/ruixen.com0.2Mar 1, 2024by jafioti

AI Summary

A major update introducing new neural network modules, support for Mistral AI, and improvements to quantization.

Key Highlights

  • Introduction of Conv1D and Conv2D modules for neural networks.
  • Added support for Mistral AI and Q8 Weight Quantization.
  • Improved f16 matmul performance and prompt handling.

New Features

  • Simple Pooling implementation
  • Conv1D and Conv2D modules
  • Support for Mistral AI
  • Q8 Weight Quantization
  • Improved f16 matmul and prompt generation

Full Release Notes

## What's Changed
Everything.

And also:
* Simple Pooling implementation by @TheSeamau5 in https://github.com/jafioti/luminal/pull/4
* Conv1D module by @TheSeamau5 in https://github.com/jafioti/luminal/pull/7
* Conv2d by @TheSeamau5 in https://github.com/jafioti/luminal/pull/8
* Add support for Mistral by @TheSeamau5 in https://github.com/jafioti/luminal/pull/9
* Shell script to download mistral that actually works by @TheSeamau5 in https://github.com/jafioti/luminal/pull/10
* Fix swish by @TheSeamau5 in https://github.com/jafioti/luminal/pull/11
* Minor improvement to f16 matmul, Longer prompt and token generation for testing by @TheSeamau5 in https://github.com/jafioti/luminal/pull/12
* Small Improvements to main by @TheSeamau5 in https://github.com/jafioti/luminal/pull/17
* Q8 Weight Quantization by @jafioti in https://github.com/jafioti/luminal/pull/24


**Full Changelog**: https://github.com/jafioti/luminal/compare/0.1...0.2