onnxruntime/onnxruntime/test
Tianlei Wu 7bc6dcecf7
fix embed layer norm fusion with embedding sum output (#17460)
The embedding sum could be graph output (when exporting with output
hidden state enabled). Previously, we only check whether there are
multiple children node to decide whether to output embedding sum in
fused node. This fix will check if the sum is graph output, we will
retain the name.
2023-09-07 22:01:26 -07:00
..
common [C#, CPP] Introduce Float16/BFloat16 support and tests for C#, C++ (#16506) 2023-07-14 10:46:52 -07:00
contrib_ops Flash Attention v2 MHA (#17227) 2023-08-31 13:52:21 -07:00
custom_op_registration Support custom ops taking float 8 tensors as inputs and outputs (#16323) 2023-07-06 14:36:06 +02:00
debug_node_inputs_outputs
framework Fix float 8 rounding on CPU (#16940) 2023-09-07 20:48:25 +02:00
fuzzing
global_thread_pools Allow RunAsync with global TP (#17157) 2023-08-15 14:29:10 -07:00
ir
logging_apis
mlas Upgrade Centos7 to Alamlinux8 (#16907) 2023-08-29 21:05:36 -07:00
onnx [QNN EP] GridSample op support (#17317) 2023-08-29 11:41:59 -07:00
opaque_api
optimizer Support QDQ transformations with com.microsoft.Quantize/Dequantize ops (#17127) 2023-08-25 09:57:51 -07:00
perftest Add checks for session options and fix gsubgraph fallback exceptions (#17095) 2023-08-16 10:06:25 -07:00
platform
proto
providers [QNN EP] Add more op unit tests (#17424) 2023-09-06 18:36:09 -07:00
python fix embed layer norm fusion with embedding sum output (#17460) 2023-09-07 22:01:26 -07:00
quantization remove AllocatorMgr class (#16509) 2023-06-28 15:43:19 -07:00
shared_lib Introduce output type/shape validation (#17301) 2023-09-05 15:25:12 -07:00
testdata Fix float 8 rounding on CPU (#16940) 2023-09-07 20:48:25 +02:00
unittest_main Enable verbose logging in unit test program with environment variable. (#17133) 2023-08-22 12:13:52 -07:00
util [CoreML EP] Add Shape, Gather, and Slice ops (#17153) 2023-08-18 22:34:34 -07:00
wasm
win_getopt
xctest