saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-26 22:35:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/test
History
JiCheng 686d42e6c8
layer_norm_fix (#15844) 
### Description
Fix bugs of Layernorm Fusion.
More checks on ReduceMean axes
separate out  layernorm transform_test

### Motivation and Context
Our layernorm fusion pattern works only for axis=-1 currently.
- For training senario: The pattern produced error results directly as
they didn't handle "axes" and only assumed it's the default vaue.
- For Inference:   
                 ~~We lost some oppotunities to fuse layernrom. ~~

ReduceMean has default axes 0 which means reduce on all dimensions
2023-05-09 22:09:00 +08:00
..
api_tests_without_env Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
common Implement two easier random tensor generator (RTG) for flaky tests (#15517) 2023-04-25 17:52:44 -07:00
contrib_ops Bring back SLN cuda kernel and use provider options to switch to standard implementation (#15660) 2023-05-01 18:35:26 -07:00
custom_op_registration Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
debug_node_inputs_outputs
framework ExecutionProvider API refactor - replace OrtMemoryInfo with OrtDevice (#15618) 2023-05-01 10:06:00 -07:00
fuzzing Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
global_thread_pools Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
ir Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
logging_apis Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
mlas NhwcFusedConv: Add before Activation (#15837) 2023-05-08 21:02:35 -07:00
onnx ExecutionProvider API refactor - replace OrtMemoryInfo with OrtDevice (#15618) 2023-05-01 10:06:00 -07:00
opaque_api Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
optimizer layer_norm_fix (#15844) 2023-05-09 22:09:00 +08:00
perftest [VitisAI]Update VitisAI EP to be compatible with VitisAI 3.5 (#15673) 2023-05-01 08:28:26 -07:00
platform Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
proto
providers [QNN EP] Update default QNN SDK to version 2.10.0 (#15818) 2023-05-05 13:01:21 -07:00
python Expose build information in dynamic lib (#15643) 2023-04-28 21:57:31 -07:00
quantization
shared_lib Implement lite custom op API (#15778) 2023-05-04 09:49:17 -07:00
testdata Implement lite custom op API (#15778) 2023-05-04 09:49:17 -07:00
unittest_main [TensorRT EP] avoid excessive library load/unload overhead when running unit tests. (#15639) 2023-04-24 14:43:13 -07:00
util Bring back SLN cuda kernel and use provider options to switch to standard implementation (#15660) 2023-05-01 18:35:26 -07:00
wasm Bump engine.io from 6.4.0 to 6.4.2 in /onnxruntime/test/wasm (#15798) 2023-05-04 05:43:40 +00:00
win_getopt Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
xctest Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00