Starstruk Logo MarkStarstruk

0.2

sxyazi/yazi0.2Mar 1, 2024by jafioti

AI Summary

This release, described as 'Everything', introduces new neural network modules, support for the Mistral model, and weight quantization capabilities, alongside improvements to matmul performance and testing infrastructure.

Key Highlights

  • Added support for the Mistral model.
  • Implemented new modules: Simple Pooling, Conv1D, and Conv2d.
  • Introduced Q8 Weight Quantization.
  • Improved f16 matmul performance and extended prompt generation for testing.

New Features

  • Simple Pooling implementation
  • Conv1D module
  • Conv2d module
  • Support for Mistral
  • Q8 Weight Quantization

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