FEAT : Adding BitNet quantization method to HFQuantizer (#33410)

Browse Source

* rebasing changes

* fixing style

* adding some doc to functions

* remove bitblas

* change dtype

* fixing check_code_quality

* fixing import order

* adding doc to tree

* Small update on BitLinear

* adding some tests

* sorting imports

* small update

* reformatting

* reformatting

* reformatting with ruff

* adding assert

* changes after review

* update disk offloading

* adapting after review

* Update after review

* add is_serializable back

* fixing style

* adding serialization test

* make style

* small updates after review

...

This commit is contained in:

Mohamed Mekkouri

2024-10-09 17:51:41 +02:00

committed by GitHub

parent 48461c0fe2

commit 36d410dab6

11 changed files with 745 additions and 1 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

tests/quantization/bitnet_integration/__init__.py Normal file