Skip to content

0.48.1

Latest

Choose a tag to compare

@matthewdouglas matthewdouglas released this 02 Oct 17:47
· 3 commits to main since this release

This release fixes a regression introduced in 0.48.0 related to LLM.int8(). This issue caused poor inference results with pre-quantized checkpoints in HF transformers.

What's Changed

Full Changelog: 0.48.0...0.48.1