frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[AOTI] Enable OP test__weight_int4pack_mm_with_scales_and_zeros in AOTI. (#155780)

Browse Source 
The op test__weight_int4pack_mm_with_scales_and_zeros is for Intel GPU. It is functionally equivalent to the CUDA/CPU op test__weight_int4pack_mm (with the constraint that oneDNN only supports integer zero points, which is why we need this API). Since test__weight_int4pack_mm is already included in AOTI's fallback list, this PR adds support for XPU.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/155780
Approved by: https://github.com/jansel
This commit is contained in:
xinan.lin
2025-06-11 22:50:25 -07:00
committed by PyTorch MergeBot
parent 463fe36532
commit 670dab6c63
3 changed files with 78 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
torchgen/aoti/fallback_ops.py
View File

@ -169,4 +169,5 @@ inductor_fallback_ops: dict[str, dict[str, list[str]]] = {
"aten.view_as_complex.default": {},
"aten.view_as_real.default": {},
"aten.view.dtype": {},
"aten._weight_int4pack_mm_with_scales_and_zeros.default": {},
}