-
Notifications
You must be signed in to change notification settings - Fork 2.9k
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
[TensorRT EP] Weightless API integration #20412
Merged
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
kevinch-nv
reviewed
May 24, 2024
moraxu
approved these changes
May 24, 2024
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.
Thank you for taking on this work!
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
Outdated
Show resolved
Hide resolved
onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
Outdated
Show resolved
Hide resolved
jywu-msft
previously approved these changes
May 25, 2024
jywu-msft
reviewed
May 26, 2024
jywu-msft
reviewed
May 26, 2024
jywu-msft
reviewed
May 26, 2024
jywu-msft
previously approved these changes
May 26, 2024
jywu-msft
approved these changes
May 26, 2024
yf711
added a commit
that referenced
this pull request
Jun 21, 2024
This PR includes the weight-stripped engine feature (thanks @moraxu for the #20214) which is the major feature for TRT 10 integration. Two TRT EP options are added: - `trt_weight_stripped_engine_enable`: Enable weight-stripped engine build and refit. - `trt_onnx_model_folder_path`: In the quick load case using embedded engine model / EPContext mode, the original onnx filename is in the node's attribute, and this option specifies the directory of that onnx file if needed. Normal weight-stripped engine workflow: ![image](https://github.com/microsoft/onnxruntime/assets/54722500/9f314865-cbda-4979-a7ac-b31c7a553b56) Weight-stripped engine and quick load workflow: ![image](https://github.com/microsoft/onnxruntime/assets/54722500/9f31db51-a7a8-495b-ba25-54c7f904cbad) see the doc [here ](https://onnxruntime.ai/docs/execution-providers/TensorRT-ExecutionProvider.html#tensorrt-ep-caches)for more information about EPContext model. --------- Co-authored-by: yf711 <[email protected]> Co-authored-by: Ye Wang <[email protected]> Co-authored-by: Michal Guzek <[email protected]> Co-authored-by: pengwa <[email protected]> Co-authored-by: wejoncy <[email protected]> Co-authored-by: Yi Zhang <[email protected]> Co-authored-by: Yi Zhang <[email protected]> Co-authored-by: Pranav Sharma <[email protected]> Co-authored-by: Adam Pocock <[email protected]> Co-authored-by: cao lei <[email protected]> Co-authored-by: Adrian Lizarraga <[email protected]> Co-authored-by: inisis <[email protected]> Co-authored-by: Jeff Bloomfield <[email protected]> Co-authored-by: mo-ja <[email protected]> Co-authored-by: kunal-vaishnavi <[email protected]> Co-authored-by: Sumit Agarwal <[email protected]> Co-authored-by: Atanas Dimitrov <[email protected]> Co-authored-by: Justin Chu <[email protected]> Co-authored-by: Yufeng Li <[email protected]> Co-authored-by: Dhruv Matani <[email protected]> Co-authored-by: Dhruv Matani <[email protected]> Co-authored-by: wangshuai09 <[email protected]> Co-authored-by: Xiaoyu <[email protected]> Co-authored-by: Xu Xing <[email protected]> Co-authored-by: Dmitri Smirnov <[email protected]> Co-authored-by: Rachel Guo <[email protected]> Co-authored-by: Sai Kishan Pampana <[email protected]> Co-authored-by: rachguo <[email protected]> Co-authored-by: Jian Chen <[email protected]> Co-authored-by: Shubham Bhokare <[email protected]> Co-authored-by: Yulong Wang <[email protected]> Co-authored-by: Andrew Fantino <[email protected]> Co-authored-by: Thomas Boby <[email protected]> Co-authored-by: Tianlei Wu <[email protected]> Co-authored-by: Scott McKay <[email protected]> Co-authored-by: Michal Guzek <[email protected]> Co-authored-by: George Wu <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
ep:TensorRT
issues related to TensorRT execution provider
release:1.18.1
triage:approved
Approved for cherrypicks for release
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR includes the weight-stripped engine feature (thanks @moraxu for the #20214) which is the major feature for TRT 10 integration.
Two TRT EP options are added:
trt_weight_stripped_engine_enable
: Enable weight-stripped engine build and refit.trt_onnx_model_folder_path
: In the quick load case using embedded engine model / EPContext mode, the original onnx filename is in the node's attribute, and this option specifies the directory of that onnx file if needed.Normal weight-stripped engine workflow:
Weight-stripped engine and quick load workflow:
see the doc here for more information about EPContext model.