mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-12 17:57:38 +00:00
950fe5e28b
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
51 lines
2.3 KiB
Python
51 lines
2.3 KiB
Python
# -------------------------------------------------------------------------
|
|
# Copyright (c) Microsoft Corporation. All rights reserved.
|
|
# Licensed under the MIT License.
|
|
# --------------------------------------------------------------------------
|
|
"""
|
|
ONNX Runtime is a performance-focused scoring engine for Open Neural Network Exchange (ONNX) models.
|
|
For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://aka.ms/onnxruntime/>`_
|
|
or the `Github project <https://github.com/microsoft/onnxruntime/>`_.
|
|
"""
|
|
__version__ = "1.8.1"
|
|
__author__ = "Microsoft"
|
|
|
|
# we need to do device version validation (for example to check Cuda version for an onnxruntime-training package).
|
|
# in order to know whether the onnxruntime package is for training it needs
|
|
# to do import onnxruntime.training.ortmodule first.
|
|
# onnxruntime.capi._pybind_state is required before import onnxruntime.training.ortmodule.
|
|
# however, import onnxruntime.capi._pybind_state will already raise an exception if a required Cuda version
|
|
# is not found.
|
|
# here we need to save the exception and continue with Cuda version validation in order to post
|
|
# meaningful messages to the user.
|
|
# the saved exception is raised after device version validation.
|
|
try:
|
|
from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, set_seed, \
|
|
RunOptions, SessionOptions, set_default_logger_severity, enable_telemetry_events, disable_telemetry_events, \
|
|
NodeArg, ModelMetadata, GraphOptimizationLevel, ExecutionMode, ExecutionOrder, SessionIOBinding, \
|
|
OrtAllocatorType, OrtMemType, OrtArenaCfg, OrtMemoryInfo, create_and_register_allocator, OrtSparseFormat
|
|
import_capi_exception = None
|
|
except Exception as e:
|
|
import_capi_exception = e
|
|
|
|
from onnxruntime.capi import onnxruntime_validation
|
|
|
|
if import_capi_exception:
|
|
raise import_capi_exception
|
|
|
|
from onnxruntime.capi.onnxruntime_inference_collection import InferenceSession, IOBinding, OrtValue, SparseTensor, \
|
|
OrtDevice
|
|
|
|
from onnxruntime.capi.training import * # noqa: F403
|
|
|
|
# TODO: thiagofc: Temporary experimental namespace for new PyTorch front-end
|
|
try:
|
|
from . import experimental
|
|
except ImportError:
|
|
pass
|
|
|
|
from onnxruntime.capi.onnxruntime_validation import package_name, version, cuda_version
|
|
if version:
|
|
__version__ = version
|
|
|
|
onnxruntime_validation.check_distro_info()
|