..
math
activation_op_test.cc
attention_lstm_data_gen.py
Format all python files under onnxruntime with black and isort ( #11324 )
2022-04-26 09:35:16 -07:00
attention_lstm_op_test.cc
Change some const to constexpr in unit tests code( #10002 )
2021-12-10 12:26:59 -08:00
attention_op_test.cc
Zhanyao/attention ( #10545 )
2022-02-17 09:02:45 -08:00
bias_dropout_op_test.cc
[CUDA] Implement BitmaskDropout, BitmaskBiasDropout and BitmaskDropoutGrad ( #11534 )
2022-05-27 17:24:47 +08:00
bias_softmax_op_test.cc
bifurcation_detector_op_test.cc
bitmask_dropout_op_test.cc
[CUDA] Implement BitmaskDropout, BitmaskBiasDropout and BitmaskDropoutGrad ( #11534 )
2022-05-27 17:24:47 +08:00
cdist_op_test.cc
conv_transpose_with_dynamic_pads_test.cc
crop_and_resize_op_test.cc
crop_op_test.cc
decoder_attention_op_test.cc
Introduce a way to disable Abseil library ( #11353 )
2022-04-27 08:57:52 -07:00
dynamic_quantize_matmul_test.cc
Change TensorShape to typically not allocate heap memory ( #9542 )
2021-11-08 10:29:54 -08:00
dynamic_slice_op_test.cc
element_wise_ops_test.cc
[ROCm] UTs and code clean up ( #10511 )
2022-02-11 08:23:25 -08:00
embed_layer_norm_op_test.cc
embed_layer_norm_test_vectors.h
expand_dims_test.cc
fastgelu_op_test.cc
Revert "fixed point based requantization on arm64 ( #11540 )" ( #11732 )
2022-06-03 19:12:25 -07:00
fft_op_test.cc
function_ops_test.cc
Consolidate utils::ToTensorProtoElementType, TypeToDataType, and data_types_internal::ToTensorDataType. ( #9824 )
2022-04-20 12:45:53 -07:00
function_test_util.cc
Add function body for SoftmaxCrossEntropyLossGrad ( #10779 )
2022-04-05 10:52:40 -07:00
function_test_util.h
Consolidate utils::ToTensorProtoElementType, TypeToDataType, and data_types_internal::ToTensorDataType. ( #9824 )
2022-04-20 12:45:53 -07:00
fused_conv_test.cc
fuse Conv+Add+activation for CPU from different op-branch ( #10987 )
2022-04-01 09:25:17 +08:00
fused_matmul_op_test.cc
[ROCm] BFloat16 support ( #10465 )
2022-02-07 22:55:15 -08:00
gridsample_test.cc
inverse_test.cc
layer_norm_op_test.cc
Enable LayerNorm and SkipLayerNorm in OneDNN EP ( #11128 )
2022-04-08 23:10:13 -07:00
layer_norm_test.cc
Transformer model CUDA EP align with CPU on corner case ( #9889 )
2022-02-03 12:58:49 -08:00
longformer_attention_op_test.cc
matmul_integer16_test.cc
matmul_integer_to_float_test.cc
add fallback of s8s8 support on x64 ( #9995 )
2021-12-10 11:33:19 -08:00
maxpool_mask_test.cc
murmur_hash3_test.cc
ngram_repeat_block_op_test.cc
nhwc_maxpool_op_test.cc
add int8_t support for pool operators ( #9852 )
2021-11-29 18:43:43 -08:00
op_reg_test.cc
qembed_layer_norm_op_test.cc
Set default quantization weight type to int8 ( #10209 )
2022-01-11 14:24:57 -08:00
qlinear_binary_op_test.cc
[NNAPI QDQ] AddQDQAdd/Mul, update to NNAPI QDQ handling, update some test settings ( #10483 )
2022-02-08 20:44:15 -08:00
qlinear_concat_test.cc
Support only one input in QLinearConcat ( #11265 )
2022-04-19 20:55:51 -07:00
qlinear_global_average_pool_test.cc
add int8_t support for pool operators ( #9852 )
2021-11-29 18:43:43 -08:00
qlinear_lookup_table_test.cc
qlinear_pool_test.cc
add int8_t support for pool operators ( #9852 )
2021-11-29 18:43:43 -08:00
quant_gemm_test.cc
fix unit test of quant gemm ( #10469 )
2022-02-07 09:14:37 -08:00
quantize_attention_op_test.cc
Implementation of QAttention for the DNNL execution provider ( #10004 )
2021-12-10 21:50:13 -08:00
quantize_lstm_op_test.cc
Change TensorShape to typically not allocate heap memory ( #9542 )
2021-11-08 10:29:54 -08:00
quantize_ops_test.cc
sample_op_test.cc
signal_ops_test.cc
skiplayernorm_op_test.cc
Transformer model CUDA EP align with CPU on corner case ( #9889 )
2022-02-03 12:58:49 -08:00
snpe_op_test.cc
EP factory creation cleanup and enhancements. ( #11798 )
2022-06-16 07:01:41 +10:00
tensor_op_test.cc
OpenVINO-EP v4.0 Release PR with OpenVINO 2022.1 ( #11025 )
2022-04-06 13:30:33 -07:00
tokenizer_test.cc
Change some const to constexpr in unit tests code( #10002 )
2021-12-10 12:26:59 -08:00
torch_embedding_shape_inference_test.cc
trilu_test.cc
unique_op_test.cc
Reduce number of memory allocations based on a customer profiling case ( #10193 )
2022-01-24 10:40:46 -08:00
word_conv_embedding_test.cc