| .. |
|
compute_optimizer
|
fix axis of layernorm for UpstreamReshape (#18425)
|
2023-11-16 16:29:00 +08:00 |
|
layout_transformation
|
[WebNN EP] Infer the layout via ONNX domain for Resize (#18871)
|
2023-12-21 11:30:29 -08:00 |
|
qdq_transformer
|
Handle all float types in IsQDQPairSupported (#19085)
|
2024-01-11 15:16:44 -08:00 |
|
selectors_actions
|
[JS/Web]Added FusedConv. (#17766)
|
2023-11-01 15:34:51 -07:00 |
|
transpose_optimization
|
Update transpose optimization to be more QDQ aware (#18444)
|
2023-11-23 08:27:47 +10:00 |
|
attention_fusion.cc
|
Add Bert/GPT2 fusion change for new attribute mask_filter_value in ORT optimizer (#14333)
|
2023-01-19 12:52:09 -08:00 |
|
attention_fusion.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
attention_fusion_helper.h
|
Replace float_t with float (#16484)
|
2023-06-27 09:28:38 -07:00 |
|
bias_dropout_fusion.cc
|
|
|
|
bias_dropout_fusion.h
|
|
|
|
bias_gelu_fusion.cc
|
[CUDA] Optimize BiasGelu/BiasGeluGrad Kernel (#16608)
|
2023-07-07 08:28:38 +08:00 |
|
bias_gelu_fusion.h
|
|
|
|
bias_softmax_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
bias_softmax_fusion.h
|
|
|
|
cast_elimination.cc
|
|
|
|
cast_elimination.h
|
|
|
|
common_subexpression_elimination.cc
|
Support QDQ transformations with com.microsoft.Quantize/Dequantize ops (#17127)
|
2023-08-25 09:57:51 -07:00 |
|
common_subexpression_elimination.h
|
|
|
|
concat_slice_elimination.cc
|
ORTModule log clean up (#16795)
|
2023-07-26 12:42:50 +08:00 |
|
concat_slice_elimination.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
constant_folding.cc
|
Make session configuration options available to kernels via OpKernelInfo (#18897)
|
2024-01-13 10:02:43 +10:00 |
|
constant_folding.h
|
Make session configuration options available to kernels via OpKernelInfo (#18897)
|
2024-01-13 10:02:43 +10:00 |
|
constant_sharing.cc
|
ORTModule log clean up (#16795)
|
2023-07-26 12:42:50 +08:00 |
|
constant_sharing.h
|
Address performance regression with duplicate initializers across DML partitions (#16087)
|
2023-05-26 13:37:34 -07:00 |
|
conv_activation_fusion.cc
|
[js/webgpu] Add hardSigmoid activation for fusedConv (#19233)
|
2024-01-30 16:28:53 -08:00 |
|
conv_activation_fusion.h
|
|
|
|
conv_add_act_fusion.cc
|
[JS/Web]Added FusedConv. (#17766)
|
2023-11-01 15:34:51 -07:00 |
|
conv_add_act_fusion.h
|
|
|
|
conv_add_fusion.cc
|
|
|
|
conv_add_fusion.h
|
|
|
|
conv_bn_fusion.cc
|
|
|
|
conv_bn_fusion.h
|
|
|
|
conv_mul_fusion.cc
|
|
|
|
conv_mul_fusion.h
|
|
|
|
div_mul_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
div_mul_fusion.h
|
|
|
|
double_qdq_pairs_remover.cc
|
[QNN/CPU EP] Add 16-bit Quantize/Dequantize contrib ops (#17015)
|
2023-09-18 09:43:34 -07:00 |
|
double_qdq_pairs_remover.h
|
[QNN/CPU EP] Add 16-bit Quantize/Dequantize contrib ops (#17015)
|
2023-09-18 09:43:34 -07:00 |
|
dropout_elimination.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
dropout_elimination.h
|
|
|
|
dynamic_quantize_matmul_fusion.cc
|
|
|
|
dynamic_quantize_matmul_fusion.h
|
|
|
|
embed_layer_norm_fusion.cc
|
|
|
|
embed_layer_norm_fusion.h
|
|
|
|
expand_elimination.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
expand_elimination.h
|
|
|
|
fast_gelu_fusion.cc
|
Introduce float 8 types (#14731)
|
2023-05-30 13:25:58 -07:00 |
|
fast_gelu_fusion.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
free_dim_override_transformer.cc
|
|
|
|
free_dim_override_transformer.h
|
|
|
|
gather_fusion.cc
|
Support Graph Input and Initializer for GatherToSplit Fusion (#18412)
|
2023-11-15 13:46:38 +08:00 |
|
gather_fusion.h
|
Fix Gather to Split optimizer (#14478)
|
2023-02-02 13:29:44 -08:00 |
|
gelu_approximation.cc
|
|
|
|
gelu_approximation.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
gelu_fusion.cc
|
|
|
|
gelu_fusion.h
|
|
|
|
gemm_activation_fusion.cc
|
|
|
|
gemm_activation_fusion.h
|
|
|
|
gemm_sum_fusion.cc
|
|
|
|
gemm_sum_fusion.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
gemm_transpose_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
gemm_transpose_fusion.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
graph_transformer.cc
|
General INFO logging tracking occurance of GraphTransformer modification (#17819)
|
2023-10-06 17:03:26 -07:00 |
|
graph_transformer_mgr.cc
|
Re-organize the transpose optimization and layout transformation files. (#16246)
|
2023-07-07 08:24:47 +10:00 |
|
graph_transformer_mgr.h
|
|
|
|
graph_transformer_utils.cc
|
Make session configuration options available to kernels via OpKernelInfo (#18897)
|
2024-01-13 10:02:43 +10:00 |
|
identical_children_consolidation.cc
|
Fix static analysis bug (#16114)
|
2023-05-28 10:58:07 -07:00 |
|
identical_children_consolidation.h
|
Fix static analysis bug (#16114)
|
2023-05-28 10:58:07 -07:00 |
|
identity_elimination.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
identity_elimination.h
|
|
|
|
initializer.cc
|
[js] enable external data loading for ort-web (#19087)
|
2024-01-12 19:24:24 -08:00 |
|
initializer.h
|
Introduce new optimizer MatMul + BatchNormalization (#17915)
|
2023-10-24 19:41:10 -07:00 |
|
insert_cast_transformer.cc
|
Fix cast removal bug (#17953)
|
2023-10-31 15:48:32 -07:00 |
|
insert_cast_transformer.h
|
Refine cast optimizer for safety (#15658)
|
2023-04-28 09:32:54 -07:00 |
|
isinf_reducesum_fusion.cc
|
Introduce float 8 types (#14731)
|
2023-05-30 13:25:58 -07:00 |
|
isinf_reducesum_fusion.h
|
|
|
|
layer_norm_fusion.cc
|
Layer norm fusion deepspeed stage3 changes (#17614)
|
2023-09-21 14:16:41 -07:00 |
|
layer_norm_fusion.h
|
Fix simplified layer norm fusion for training (#14866)
|
2023-03-07 13:59:20 -08:00 |
|
matmul_activation_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
matmul_activation_fusion.h
|
[DML EP] Add MatMul + SoftMax fusion (#15240)
|
2023-04-11 08:31:04 -07:00 |
|
matmul_add_fusion.cc
|
|
|
|
matmul_add_fusion.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
matmul_bn_fusion.cc
|
Introduce new optimizer MatMul + BatchNormalization (#17915)
|
2023-10-24 19:41:10 -07:00 |
|
matmul_bn_fusion.h
|
Introduce new optimizer MatMul + BatchNormalization (#17915)
|
2023-10-24 19:41:10 -07:00 |
|
matmul_integer_to_float.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
matmul_integer_to_float.h
|
|
|
|
matmul_scale_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
matmul_scale_fusion.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
matmul_transpose_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
matmul_transpose_fusion.h
|
|
|
|
nchwc_transformer.cc
|
|
|
|
nchwc_transformer.h
|
|
|
|
nhwc_transformer.cc
|
Re-organize the transpose optimization and layout transformation files. (#16246)
|
2023-07-07 08:24:47 +10:00 |
|
nhwc_transformer.h
|
Re-organize the transpose optimization and layout transformation files. (#16246)
|
2023-07-07 08:24:47 +10:00 |
|
noop_elimination.cc
|
|
|
|
noop_elimination.h
|
|
|
|
not_where_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
not_where_fusion.h
|
|
|
|
optimizer_execution_frame.cc
|
Make session configuration options available to kernels via OpKernelInfo (#18897)
|
2024-01-13 10:02:43 +10:00 |
|
optimizer_execution_frame.h
|
Make session configuration options available to kernels via OpKernelInfo (#18897)
|
2024-01-13 10:02:43 +10:00 |
|
pad_fusion.cc
|
Fix crash in PadFusion (#18557)
|
2023-12-22 11:03:34 -08:00 |
|
pad_fusion.h
|
Introduce new optimizer Pad + Conv/MaxPool (#18136)
|
2023-11-03 07:17:02 -07:00 |
|
pre_shape_node_elimination.cc
|
Eliminate safe nodes that are followed by a shape node. (#16065)
|
2023-06-26 16:35:07 +08:00 |
|
pre_shape_node_elimination.h
|
Eliminate safe nodes that are followed by a shape node. (#16065)
|
2023-06-26 16:35:07 +08:00 |
|
propagate_cast_ops.cc
|
Zhijxu/cast propagation softmax (#16408)
|
2023-06-25 10:28:54 +08:00 |
|
propagate_cast_ops.h
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
quick_gelu_fusion.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
quick_gelu_fusion.h
|
|
|
|
relu_clip_fusion.cc
|
|
|
|
relu_clip_fusion.h
|
|
|
|
reshape_fusion.cc
|
ORTModule log clean up (#16795)
|
2023-07-26 12:42:50 +08:00 |
|
reshape_fusion.h
|
|
|
|
rocm_blas_alt_impl.cc
|
|
|
|
rocm_blas_alt_impl.h
|
|
|
|
rule_based_graph_transformer.cc
|
Run clang-format in CI (#15524)
|
2023-04-18 09:26:58 -07:00 |
|
skip_layer_norm_fusion.cc
|
Broadcasting for SLN for CPU and CUDA (#16510)
|
2023-08-07 09:55:42 -07:00 |
|
skip_layer_norm_fusion.h
|
|
|
|
slice_elimination.cc
|
|
|
|
slice_elimination.h
|
|
|
|
transformer_memcpy.cc
|
[ORTModule] ATen Efficient Attention and Triton Flash Attention (#17959)
|
2023-10-27 10:29:27 +08:00 |
|
transformer_memcpy.h
|
|
|
|
transpose_optimizer.cc
|
Resize and EP specific transpose optimization updates (#17664)
|
2023-09-29 08:11:36 +10:00 |
|
transpose_optimizer.h
|
Resize and EP specific transpose optimization updates (#17664)
|
2023-09-29 08:11:36 +10:00 |
|
unsqueeze_elimination.cc
|
|
|
|
unsqueeze_elimination.h
|
|
|
|
utils.cc
|
Support QDQ transformations with com.microsoft.Quantize/Dequantize ops (#17127)
|
2023-08-25 09:57:51 -07:00 |
|
utils.h
|
Add Bert/GPT2 fusion change for new attribute mask_filter_value in ORT optimizer (#14333)
|
2023-01-19 12:52:09 -08:00 |
