Skip to content

fix repeat IS_TRT_VERSION_GE #75975

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Oct 24, 2025
Merged

fix repeat IS_TRT_VERSION_GE #75975

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions paddle/fluid/inference/tensorrt/engine.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,11 +196,7 @@ bool TensorRTEngine::Enqueue(nvinfer1::IExecutionContext *context,
if (!with_dynamic_shape()) {
ret = context->enqueue(batch_size, buffers->data(), stream, nullptr);
} else {
#if IS_TRT_VERSION_GE(8500)
Copy link
Contributor

@lizexu123 lizexu123 Oct 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这是支持trt的enqueueV3接口，不能删除

Copy link
Contributor Author

@co63oc co63oc Oct 22, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

image 这里有重复的enqueueV3调用 @lizexu123

Copy link
Contributor

@lizexu123 lizexu123 Oct 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

如果TensorRT版本大于8.5,且我们用的是静态shape，按照你这个逻辑，不久跑到了enqueue接口去了？

Copy link
Contributor Author

@co63oc co63oc Oct 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

image 加了注释这样容易查看

ret = context->enqueueV3(stream);
#else
ret = context->enqueueV2(buffers->data(), stream, nullptr);
#endif
}
#endif
return ret;
Expand Down
Loading