onnxruntime/include/onnxruntime/core/framework
Dmitri Smirnov 950fe5e28b
Implement SparseTensor and infrastructure suppport and advance ONNX commit (#8038)
SparseTensor support
  Implement Builder pattern
  Fix support for 1-D and 2-D COO indices
  Implement and test CSR support.
  Handle shape inference for SparseTensors
  Implement conversion for COO, CSR and tests.
  Address the case where constant sparse initializer is the output.
  Implement test infra for SparseTensors
  Implement SparseDenseMatMul for Csr and COO and tested it.
  Add hash for SparseToDenseMatMul
  Finish shared provider refactor
  Refactor GetOrCreate to Create
  Working on py interface
  Expose OrtDevice and use it in allocate_numpy
	Adjust Sparse interfaces, add support for string SparseTensor. Add tests.
	Add and test to_cuda()
	Add accessors to format specific indices
	Test values and indices views, read-only flag, after GC access
	Add sparse related methods to OrtValue
	Re-work SparseTensor wrapper, add OrtValue methods
	Rework numpy_array_to_cuda/to_cpu
	Add run_with_ort_values
	Add models and test sparse_mat_mul with run_with_ort_values
	Refactor sparse tensor to use a single buffer
        Ifdef x86 Eigen CSR sparse matmul implementation
        Exclude broken test, check for string type when copying cross device
       Split pybind schema, regenerate docs, add exclusion
       Conditionally exclude schema module
       Update docs fix cuda build
       Add test to a filter and renerate JS docs
      Add conversion and test string support for sparse tensors
      Exclude conversion utils from minimal build
      Add CUDA Memcpy and adjust provider interfaces
2021-07-22 15:24:36 -07:00
..
alloc_kind.h Add New AllocKind for YieldOp Outputs, Run YieldOp with InferenceSession in UT (#7125) 2021-03-25 15:18:51 +08:00
allocator.h Support plugging in custom user-defined allocators for sharing between sessions (#8059) 2021-07-22 10:17:35 -07:00
buffer_deleter.h Add ability for pre-packed weights of shared initializers to be shared across sessions (#7421) 2021-05-14 20:44:42 -07:00
customregistry.h Sync ORTModule branch with master and fix tests (#6526) 2021-02-02 08:59:56 -08:00
data_types.h Implement SparseTensor and infrastructure suppport and advance ONNX commit (#8038) 2021-07-22 15:24:36 -07:00
data_types_internal.h Update C++ Standard from 14 to 17 (#8041) 2021-06-25 14:08:01 -07:00
endian.h Edgchen1/endian utils (#2181) 2019-10-21 22:28:35 -07:00
execution_provider.h Change onnxruntime::make_unique to std::make_unique (#7502) 2021-04-29 17:04:53 -07:00
fence.h Remove Cuda dependency from TensorRT shared provider (#5014) 2020-09-04 11:35:02 -07:00
float16.h Update C++ Standard from 14 to 17 (#8041) 2021-06-25 14:08:01 -07:00
framework_common.h
func_api.h Sync ORTModule branch with master and fix tests (#6526) 2021-02-02 08:59:56 -08:00
kernel_def_builder.h Remove some templated versions of functions that are no longer needed (#7868) 2021-05-28 13:22:45 -07:00
kernel_registry.h Check kernel def hashes (#7120) 2021-04-01 17:42:58 -07:00
ml_value.h Implement SparseTensor and infrastructure suppport and advance ONNX commit (#8038) 2021-07-22 15:24:36 -07:00
op_kernel.h Implement SparseTensor and infrastructure suppport and advance ONNX commit (#8038) 2021-07-22 15:24:36 -07:00
op_kernel_context.h Implement SparseTensor and infrastructure suppport and advance ONNX commit (#8038) 2021-07-22 15:24:36 -07:00
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 Ryanunderhill/cuda shared (#7626) 2021-05-20 07:53:47 -07:00
ortdevice.h Sync ORTModule branch with master and fix tests (#6526) 2021-02-02 08:59:56 -08:00
ortmemoryinfo.h Remove Cuda dependency from TensorRT shared provider (#5014) 2020-09-04 11:35:02 -07:00
provider_options.h Sync ORTModule branch with master and fix tests (#6526) 2021-02-02 08:59:56 -08:00
provider_options_utils.h Plug n Allocate with external CUDA allocator via PyBind. (#6679) 2021-02-17 18:59:38 -08:00
provider_shutdown.h Fix shared provider unload crash (#5553) 2020-10-21 13:01:21 -07:00
run_options.h Add ability for memory arenas to "shrink" periodically (#7284) 2021-05-08 07:53:21 -07:00
sparse_tensor.h Implement SparseTensor and infrastructure suppport and advance ONNX commit (#8038) 2021-07-22 15:24:36 -07:00
tensor.h Support plugging in custom user-defined allocators for sharing between sessions (#8059) 2021-07-22 10:17:35 -07:00
tensor_shape.h Filter out info from non-const initializers during shape inferencing (#1806) 2019-09-26 13:44:33 +10:00