Tianlei Wu 72186bbb71 [CUDA] Build nhwc ops by default (#22648) ... ### Description * Build cuda nhwc ops by default. * Deprecate `--enable_cuda_nhwc_ops` in build.py and add `--disable_cuda_nhwc_ops` option Note that it requires cuDNN 9.x. If you build with cuDNN 8, NHWC ops will be disabled automatically. ### Motivation and Context In general, NHWC is faster than NCHW for convolution in Nvidia GPUs with Tensor Cores, and this could improve performance for vision models. This is the first step to prefer NHWC for CUDA in 1.21 release. Next step is to do some tests on popular vision models. If it help in most models and devices, set `prefer_nhwc=1` as default cuda provider option.		2024-11-06 09:54:55 -08:00
..
android_custom_build	Update Android NDK version to 27.0.12077973. (#21989)	2024-09-05 17:57:24 -07:00
ci_build	[CUDA] Build nhwc ops by default (#22648)	2024-11-06 09:54:55 -08:00
doc	Update ruff and clang-format versions (#21479)	2024-07-24 11:50:11 -07:00
nuget	[DML EP] Update DML to 1.15.4 (#22635)	2024-10-29 17:13:57 -07:00
perf_view	fixed #16873 (#16932)	2023-09-26 09:57:01 -07:00
python	update pipeline name list in run_CIs_for_external_pr.py (#22540)	2024-10-22 17:14:48 -07:00
scripts	Update DNNL CI python to 310 (#22691)	2024-11-05 09:14:48 -08:00