[OVEP] Expose kvcache_rewind python api #831
Open
Conversation
This file contains hidden or 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
ankitm3k
force-pushed
the
expose_python_api
branch
from
998fda7 to
476d46e
Compare
mklimenk
suggested changes
Oct 13, 2025
| #endif | ||
| }) | ||
| .def( | ||
| "set_ep_dynamic_options", [](PyInferenceSession* sess, const py::dict& options) -> void { |
There was a problem hiding this comment.
Explicit return type in lambda is unnecessary starting with C++14. On top of that, -> void doesn't provide any additional information.
Some of the functions in this file use it, but not all of them. So let's remove it
| gsl::make_span(values.data(), values.size())); | ||
|
|
||
| if (!status.IsOK()) { | ||
| throw std::runtime_error("Failed to set EP dynamic options: " + status.ErrorMessage()); |
There was a problem hiding this comment.
Please don't throw raw C++ exceptions. There's an example in this file on how to report an error(OrtPybindThrowIfError or ORT_THROW, depending on the build type)
| throw std::runtime_error("No options were provided"); | ||
| } | ||
|
|
||
| // Call the underlying C++ method |
|
Please attach a JIRA for this feature request in the PR description. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Description
In Phi-Silica app which didn't rely on ORT-GenAI, we need an API to remove KV history. The kvcache_rewind is an OVEP function to achieve this, however there is no python API exposed. This PR is for this purpose.