Skip to content

Commit 6b350bd

Browse files
jerryzh168facebook-github-bot
authored andcommitted
Make sure XNNPACKQuantizer works with the pre_dispatch=True
Summary: X-link: pytorch/pytorch#107872 att Reviewed By: andrewor14, tugsbayasgalan Differential Revision: D48415977 fbshipit-source-id: fc8c8bfc7ba64b53e0f3dee517c4d95462735d9c
1 parent d61d5b7 commit 6b350bd

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

backends/xnnpack/test/test_xnnpack_utils.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -307,7 +307,8 @@ def quantize_and_test_model_with_quantizer(
307307
module.eval()
308308
# program capture
309309
m = torch._export.capture_pre_autograd_graph(
310-
module, example_inputs, decomp_table=_default_decomposition_table()
310+
module,
311+
example_inputs,
311312
)
312313

313314
quantizer = XNNPACKQuantizer()

0 commit comments

Comments
 (0)