frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-21 05:34:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "[reland][quant][pt2e] Add early prototype top level quantize_pt2e APIs (#90971)"

Browse Source 
This reverts commit 7dd5e554971411cbb50fc2eb157057c1e8a0de63.

Reverted https://github.com/pytorch/pytorch/pull/90971 on behalf of https://github.com/ezyang due to still broke tons of master jobs sorry
This commit is contained in:
PyTorch MergeBot
2022-12-16 09:29:39 +00:00
parent ddf5b68dcb
commit ad1b04c4a9
7 changed files with 2 additions and 456 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
test/test_quantization.py
View File

@ -74,8 +74,6 @@ try:
from quantization.fx.test_quantize_fx import TestQuantizeFxOps # noqa: F401
from quantization.fx.test_quantize_fx import TestQuantizeFxModels # noqa: F401
from quantization.fx.test_subgraph_rewriter import TestSubgraphRewriter # noqa: F401
# Quantization for PyTorch 2.0 Export path
from quantization.fx.test_quantize_pt2e import TestQuantizePT2EModels # noqa: F401
except ImportError:
# In FBCode we separate FX out into a separate target for the sake of dev
# velocity. These are covered by a separate test target `quantization_fx`