OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2026-01-15 12:15:51 +00:00
Code Issues Actions 52 Packages Projects Releases Wiki Activity

Re-enable ConvTranspose operator benchmarks for AArch64 (#166731)

Browse Source 
This was disabled by #165585 due to #165654 which was fixed by #165904

Pull Request resolved: https://github.com/pytorch/pytorch/pull/166731
Approved by: https://github.com/malfet
ghstack dependencies: #165904
This commit is contained in:
Fadi Arafeh
2025-10-31 16:52:43 +00:00
committed by PyTorch MergeBot
parent 88d635c54f
commit f97c3fc8e4
1 changed files with 6 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
benchmarks/operator_benchmark/pt/conv_test.py
View File

@@ -43,15 +43,12 @@ op_bench.generate_pt_gradient_test(
Conv1dBenchmark,
)
if not torch.backends.mkldnn.is_acl_available():
# convtranpose1d crashes with ACL, see https://github.com/pytorch/pytorch/issues/165654
op_bench.generate_pt_test(
configs.convtranspose_1d_configs_short
+ configs.conv_1d_configs_short
+ configs.conv_1d_configs_long,
ConvTranspose1dBenchmark,
)
op_bench.generate_pt_test(
configs.convtranspose_1d_configs_short
+ configs.conv_1d_configs_short
+ configs.conv_1d_configs_long,
ConvTranspose1dBenchmark,
)
"""