saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-23 22:13:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/python
History
Chi Lo fa4cbcd36b
[TensorRT EP] Add new provider option to exclude nodes from running on TRT (#22681) 
Add new provider option `trt_op_types_to_exclude`:
- User can provide op type list to be excluded from running on TRT
- e.g. `trt_op_types_to_exclude="MaxPool"`

There is a known performance issue with the DDS ops (NonMaxSuppression,
NonZero and RoiAlign) from TRT versions 10.0 to 10.7. TRT EP excludes
DDS ops from running on TRT by default, user can override default value
with empty string to include all ops.
2024-11-13 11:34:43 -08:00
..
backend fix supports_device() in python interface (#22473) 2024-10-17 12:10:25 -07:00
datasets
providers/tvm
tools [Quant Tool] Add reduce_range option to get_qdq_config() (#22782) 2024-11-08 14:04:11 -08:00
torch_cpp_extensions
training
__init__.py
_ld_preload.py
_pybind_state.py.in
convert_npz_to_onnx_adapter.py Multi-Lora support (#22046) 2024-09-30 15:59:07 -07:00
exported_symbols.lst
numpy_helper.h fix Window_CI in Github Action (#21070) 2024-06-18 23:14:08 -07:00
onnxruntime_collect_build_info.py Remove unused find_cudnn_supported_cuda_versions (#21620) 2024-09-03 14:38:33 -07:00
onnxruntime_inference_collection.py Add implementation of WebGPU EP (#22591) 2024-10-29 18:29:40 -07:00
onnxruntime_pybind.h
onnxruntime_pybind_exceptions.cc
onnxruntime_pybind_exceptions.h
onnxruntime_pybind_iobinding.cc Support onnx data types (bfloat16, float8) in python I/O binding APIs (#22306) 2024-10-04 17:29:15 -07:00
onnxruntime_pybind_lora.cc Multi-Lora support (#22046) 2024-09-30 15:59:07 -07:00
onnxruntime_pybind_mlvalue.cc Revert Implement DML copy for Lora Adapters (#22814) 2024-11-12 17:45:59 -05:00
onnxruntime_pybind_mlvalue.h Support onnx data types (bfloat16, float8) in python I/O binding APIs (#22306) 2024-10-04 17:29:15 -07:00
onnxruntime_pybind_module.cc
onnxruntime_pybind_ortvalue.cc Distinguish between DML and the generic 'GPU' term. This is needed for packaging DML EP in the same ORT GPU pkg. (#22657) 2024-10-30 11:58:34 -07:00
onnxruntime_pybind_quant.cc [Optimizer] DQ + MatMul to MatMulNBits support: kernel changes (#21342) 2024-07-15 15:25:40 -07:00
onnxruntime_pybind_schema.cc Update Arm Compute Library Execution Provider (#22032) 2024-09-12 20:51:59 -07:00
onnxruntime_pybind_sparse_tensor.cc Update ruff and clang-format versions (#21479) 2024-07-24 11:50:11 -07:00
onnxruntime_pybind_state.cc [TensorRT EP] Add new provider option to exclude nodes from running on TRT (#22681) 2024-11-13 11:34:43 -08:00
onnxruntime_pybind_state.h Multi-Lora support (#22046) 2024-09-30 15:59:07 -07:00
onnxruntime_pybind_state_common.cc
onnxruntime_pybind_state_common.h Add implementation of WebGPU EP (#22591) 2024-10-29 18:29:40 -07:00
onnxruntime_validation.py [AIX] Python binding enablement and gcc support (#21934) 2024-08-30 12:17:26 -07:00
pybind.def
version_script.lds
version_script_expose_onnx_protobuf.lds