onnxruntime-ep-nv-tensorrt-rtx-cu13 0.3.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,94 @@
1
+ Metadata-Version: 2.4
2
+ Name: onnxruntime-ep-nv-tensorrt-rtx-cu13
3
+ Version: 0.3.0
4
+ Summary: ONNX Runtime plugin package for the NVIDIA TensorRT RTX execution provider (EP ABI)
5
+ Author: NVIDIA Corporation
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/NVIDIA/TensorRT-RTX-EP-ABI
8
+ Keywords: onnxruntime,tensorrt,execution-provider,nvidia
9
+ Classifier: Development Status :: 3 - Alpha
10
+ Classifier: Intended Audience :: Developers
11
+ Classifier: Programming Language :: Python :: 3
12
+ Classifier: Programming Language :: Python :: 3.8
13
+ Classifier: Programming Language :: Python :: 3.9
14
+ Classifier: Programming Language :: Python :: 3.10
15
+ Classifier: Programming Language :: Python :: 3.11
16
+ Classifier: Programming Language :: Python :: 3.12
17
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
18
+ Requires-Python: >=3.8
19
+ Description-Content-Type: text/markdown
20
+ Provides-Extra: dev
21
+ Requires-Dist: onnx>=1.14; extra == "dev"
22
+ Requires-Dist: numpy>=1.21; extra == "dev"
23
+ Dynamic: description
24
+ Dynamic: description-content-type
25
+
26
+ # onnxruntime-ep-nv-tensorrt-rtx
27
+
28
+ NVIDIA TensorRT RTX Execution Provider plugin for [ONNX Runtime](https://onnxruntime.ai/).
29
+
30
+ Enables hardware-accelerated inference on NVIDIA RTX GPUs (Ampere / RTX 30xx and later) via the
31
+ [ORT Plugin EP ABI](https://onnxruntime.ai/docs/execution-providers/plugin-ep-libraries.html).
32
+
33
+ ---
34
+
35
+ ## About NVIDIA TensorRT for RTX
36
+
37
+ NVIDIA® TensorRT™ for RTX (TensorRT-RTX) is an inference optimization library dedicated for
38
+ deploying AI inference on NVIDIA GeForce RTX GPUs. It is a great choice for developers building
39
+ applications that must run on Windows or Linux PCs, laptops, or workstations.
40
+
41
+ This package bundles the TensorRT-RTX runtime libraries alongside the ONNX Runtime EP plugin so
42
+ that no separate TensorRT-RTX installation is required.
43
+
44
+ For more information about TensorRT-RTX, visit https://developer.nvidia.com/tensorrt-rtx.
45
+ Online documentation: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/index.html
46
+ License agreement: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/reference/sla.html
47
+
48
+ ---
49
+
50
+ ## References
51
+
52
+ - Release Notes: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/getting-started/release-notes.html
53
+ - Support Matrix: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/getting-started/support-matrix.html
54
+ - Installation Guide: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/installing-tensorrt-rtx/installation-overview.html
55
+ - C++ API: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/_static/cpp-api/index.html
56
+ - Python API: https://docs.nvidia.com/deeplearning/tensorrt-rtx/latest/_static/python-api/index.html
57
+
58
+ ---
59
+
60
+ ## Requirements
61
+
62
+ - NVIDIA RTX GPU (Ampere or later)
63
+ - NVIDIA GPU driver with CUDA 13 support
64
+ - `pip install onnxruntime>=1.24`
65
+
66
+ ## Installation
67
+
68
+ ```bash
69
+ pip install onnxruntime>=1.24
70
+ pip install onnxruntime-ep-nv-tensorrt-rtx
71
+ ```
72
+
73
+ ## Usage
74
+
75
+ ```python
76
+ import onnxruntime as ort
77
+ import onnxruntime_ep_nv_tensorrt_rtx as trt_ep
78
+
79
+ # Register the EP plugin
80
+ ort.register_execution_provider_library(trt_ep.get_ep_name(), trt_ep.get_library_path())
81
+
82
+ # List available devices
83
+ devices = [d for d in ort.get_ep_devices() if d.ep_name == trt_ep.get_ep_name()]
84
+ print(f"TensorRT RTX devices: {len(devices)}")
85
+
86
+ # Create session with EP
87
+ so = ort.SessionOptions()
88
+ so.add_provider_for_devices(devices, {})
89
+ sess = ort.InferenceSession("model.onnx", sess_options=so)
90
+ ```
91
+
92
+ ## License
93
+
94
+ Apache 2.0. See [LICENSE](https://www.apache.org/licenses/LICENSE-2.0).
@@ -0,0 +1,10 @@
1
+ # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
+ # SPDX-License-Identifier: Apache-2
3
+
4
+ [build-system]
5
+ requires = ["wheel-stub"]
6
+ build-backend = "wheel_stub.buildapi"
7
+
8
+ [tool.wheel_stub]
9
+ index_url = "https://pypi.nvidia.com/"
10
+ include_cuda_debuginfo = true