cloudhan 14365b67a0 Fix hipify due to CUDA EP tensorrt_fused_multihead_attention optimization (#12990) ... Recent change in CUDA EP #12814 makes hipify extremely slow and breaks the building. This PR fixes it by c The onnxruntime/contrib_ops/rocm/bert/attention.h is checkout-ed from the version before #12814 and manually hipify-ed. Slightly extend amd_hipify.py to allow wildcard file match and exclude all `tensorrt_fused_multihead_attention/*` files from hipify		2022-09-19 15:29:23 +08:00
..
android_custom_build	Replace references to onnxruntime 'master' with 'main' in Dockerfiles. (#12550)	2022-08-16 14:13:05 -07:00
ci_build	Fix hipify due to CUDA EP tensorrt_fused_multihead_attention optimization (#12990)	2022-09-19 15:29:23 +08:00
doc	Format all python files under onnxruntime with black and isort (#11324)	2022-04-26 09:35:16 -07:00
nuget	[C#][TVM EP] Fix issues related to using TVM EP in C# front-end (#12958)	2022-09-16 16:04:59 +02:00
perf_view	fix json format (#11046)	2022-03-30 16:15:33 -07:00
python	Add --output_dir option to convert_onnx_models_to_ort.py. (#12844)	2022-09-12 15:36:03 -07:00