| .. |
|
alloc_kind.h
|
Avoid copy of pre-existing value to subgraph output (#637)
|
2019-03-19 06:55:59 +10:00 |
|
allocator.h
|
allocator refactor (#467)
|
2019-02-12 14:14:21 -08:00 |
|
customregistry.h
|
CustomRegistry should use composition instead of inheritence
|
2019-04-05 14:14:10 -07:00 |
|
data_types.h
|
Reduce code size of kernel registration (#833)
|
2019-04-15 16:39:59 -07:00 |
|
environment.h
|
Abbreviate ONNXRuntime as Ort in all of our public APIs (#175)
|
2018-12-14 14:54:23 -08:00 |
|
execution_provider.h
|
Support large model(>2GB) (#520)
|
2019-03-05 21:27:12 -08:00 |
|
fence.h
|
Fix memory corruption issue when CPU->CUDA memcpy is involved (#879)
|
2019-04-22 20:21:14 -07:00 |
|
framework_common.h
|
Initial bootstrap commit.
|
2018-11-19 16:48:22 -08:00 |
|
func_api.h
|
Add nGraph Execution Provider (#832)
|
2019-04-20 17:02:35 -07:00 |
|
kernel_def_builder.h
|
cleanup code (#343)
|
2019-01-16 17:12:22 -08:00 |
|
kernel_registry.h
|
Optimize graph partition
|
2019-02-20 16:32:04 -08:00 |
|
ml_value.h
|
Abbreviate ONNXRuntime as Ort in all of our public APIs (#175)
|
2018-12-14 14:54:23 -08:00 |
|
op_kernel.h
|
Simplify the validation in Run call (#850)
|
2019-04-18 08:38:17 +08:00 |
|
op_kernel_info.h
|
Simplify the validation in Run call (#850)
|
2019-04-18 08:38:17 +08:00 |
|
op_node_proto_helper.h
|
misc: Fix comment in op_node_proto_helper (#460)
|
2019-02-11 14:38:43 -08:00 |
|
run_options.h
|
Simplify the validation in Run call (#850)
|
2019-04-18 08:38:17 +08:00 |
|
tensor.h
|
Support large model(>2GB) (#520)
|
2019-03-05 21:27:12 -08:00 |
|
tensor_shape.h
|
Fix array feature extractor out of bounds access issue (#194)
|
2018-12-18 00:30:07 -08:00 |
