-
Notifications
You must be signed in to change notification settings - Fork 3.3k
Add documentation for NV TensorRT RTX ExecutionProvider #24829
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Tagging @chilo-ms @gedoensmax @ishwar-raut1 for review. |
@chilo-ms @jywu-msft any comments or suggestions ? (Not sure why the tests are failing). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR adds documentation for the NV TensorRT RTX ExecutionProvider, providing detailed instructions and code examples for both C++ and Python users.
- Introduces a new markdown file with installation, build, usage, configurations, and performance tuning sections.
- Provides illustrative code snippets and explanations for session options and EP caching mechanisms.
Comments suppressed due to low confidence (2)
docs/execution-providers/TensorRTRTX-ExecutionProvider.md:18
- There is an extra preposition in the phrasing; consider revising to "to accelerate ONNX models on RTX GPUs".
to accelerate ONNX model in on RTX GPUs.
docs/execution-providers/TensorRTRTX-ExecutionProvider.md:63
- [nitpick] The link appears to reference a file with a slightly different name than the current document; consider updating it to 'TensorRTRTX-ExecutionProvider.md' for consistency.
Here are examples and different [scenarios](./TensorRT-RTXExecutionProvider.md#scenario) to set NV TensorRT RTX EP session options:
LGTM. there are some known existing bad links which cause the failure. need to fix those. but should be unrelated to your doc |
we need to fix the other broken link checks, but looks like there are some errors for the new page you adding For the Links > Internal check, the following failures were found:
|
* Add build instructions for TRT-RTX (only windows for now) * Fix broken link
Sorry about that. Fixed. |
@jywu-msft , Any more concerns for this first revision of the documentation? Can this be merged now? |
Description
Add documentation for NV TensorRT RTX ExecutionProvider
Motivation and Context
The EP is already online. This is for adding some basic documentation for the options / features exposed by the EP.