..
alloc_kind.h
Exclude some training specific code from the minimal build. Cleanup some related aspects of allocation planner. ( #5861 )
2020-11-20 20:25:46 +10:00
allocator.h
Factor out IAllocator so that it can be shared with shared providers ( #5567 )
2020-10-27 17:28:17 -07:00
customregistry.h
data_types.h
Support opset-13 specs of controlflow ops (Loop, If) ( #5665 )
2020-11-11 23:44:14 -08:00
data_types_internal.h
Fix bug in DispatchOnTensorType macro ( #4808 )
2020-08-17 01:16:01 -07:00
endian.h
execution_provider.h
Support EPs that compile nodes in a minimal build. ( #5776 )
2020-11-17 13:52:22 +10:00
fence.h
Remove Cuda dependency from TensorRT shared provider ( #5014 )
2020-09-04 11:35:02 -07:00
framework_common.h
func_api.h
Ryanunderhill/mkldnn dll ( #3314 )
2020-05-06 00:57:09 -07:00
kernel_def_builder.h
Memory planner and pattern generation enhancements. ( #4443 )
2020-11-01 23:05:46 -08:00
kernel_registry.h
Add kernel def hash logic for minimal build ( #4891 )
2020-08-23 14:39:07 +10:00
ml_value.h
Support for Sparse Initializers ( #5540 )
2020-10-27 10:32:06 -07:00
op_kernel.h
Move GetUseDeterministicCompute() to OpKernelContext to avoid need to downcast to OpKernelContextInternal. ( #5729 )
2020-11-09 11:37:06 -08:00
op_kernel_info.h
Support EPs that compile nodes in a minimal build. ( #5776 )
2020-11-17 13:52:22 +10:00
op_node_proto_helper.h
Allow Kernels refer to some attribute data directly in the protobuf ( #5624 )
2020-10-29 16:12:54 -07:00
ortdevice.h
ROCm EP for AMD GPU ( #5480 )
2020-10-29 17:13:04 -07:00
ortmemoryinfo.h
Remove Cuda dependency from TensorRT shared provider ( #5014 )
2020-09-04 11:35:02 -07:00
provider_shutdown.h
Fix shared provider unload crash ( #5553 )
2020-10-21 13:01:21 -07:00
run_options.h
Support training_mode flag in eval ( #4324 )
2020-07-08 10:38:54 -07:00
sparse_tensor.h
Support for Sparse Initializers ( #5540 )
2020-10-27 10:32:06 -07:00
tensor.h
Support EPs that compile nodes in a minimal build. ( #5776 )
2020-11-17 13:52:22 +10:00
tensor_shape.h