FEAT : Adding VPTQ quantization method to HFQuantizer (#34770)

* init vptq * add integration * add vptq support fix readme * add tests && format * format * address comments * format * format * address comments * format * address comments * remove debug code * Revert "remove debug code" This reverts commit ed3b3eaaba82caf58cb3aa6e865d98e49650cf66. * fix test --------- Co-authored-by: Yang Wang <wyatuestc@gmail.com>
2024-12-20 16:45:53 +08:00
parent 5a2aedca1e
commit 4e27a4009d
21 changed files with 647 additions and 3 deletions
--- a/docs/source/ko/main_classes/quantization.md
+++ b/docs/source/ko/main_classes/quantization.md
@@ -35,6 +35,10 @@ Transformers에서 지원되지 않는 양자화 기법들은 [`HfQuantizer`]

 [[autodoc]] AqlmConfig

+## VptqConfig[[transformers.VptqConfig]]
+
+[[autodoc]] VptqConfig
+
 ## AwqConfig[[transformers.AwqConfig]]

 [[autodoc]] AwqConfig