v0.4.2

Bumping PyTorch version

Full Changelog: v0.4.1...v0.4.2

v0.4.1

This is the first non-pre-release version that supports auto-tune. Seems to break in some cases, so use with caution.

Full Changelog: v0.4.0...v0.4.1

v0.4.1a0

What's Changed

• Removing GPU + Shape Specialization via Autotune

Full Changelog: v0.3.0...v0.4.1a0

v0.3.0

What's Changed

• Fixes #14 by @radi-cho in #15
• Integrating fast_hadamard_transform on C++ level by @BlackSamorez in #17

Full Changelog: v0.2.6...v0.3.0

v0.2.6

Full Changelog: v0.2.4...v0.2.6

v0.2.4

bumped version number

v0.2.3

Added support for vector dequantization (with a vector size of 2)

v0.1.0

What's Changed

• Add learnable scales functionality. by @radi-cho in #8
• Better HuggingFace support.

New Contributors

• @radi-cho made their first contribution in #8

Full Changelog: v0.0.7...v0.1.0

v0.0.7

Added bitsandbytes conversion support.

v0.0.6

Patch release.

Full Changelog: v0.0.5...v0.0.6