We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
请问一下:https://github.com/PaddlePaddle/FastDeploy/blob/cc8d1f3c9f31ea4919972f14ee3eaaa9a09966e2/fastdeploy/runtime/backends/ort/ort_backend.cc#L203C22-L203C38 这里的std::vector<char*> disable_fp16_ops;是怎么管理内存的 还有
std::vector<char*> disable_fp16_ops;
FastDeploy/fastdeploy/runtime/backends/ort/ort_backend.cc
Line 255 in cc8d1f3
char* model_content_ptr
The text was updated successfully, but these errors were encountered:
disable_fp16_ops 里的内存看着有点泄漏,实际应该要在paddle2onnx使用完之后手动释放下。 你帮忙提个pr修复下?
Sorry, something went wrong.
model_content_ptr 是有手动管理并释放的
已提PR修复
heliqi
No branches or pull requests
请问一下:https://github.com/PaddlePaddle/FastDeploy/blob/cc8d1f3c9f31ea4919972f14ee3eaaa9a09966e2/fastdeploy/runtime/backends/ort/ort_backend.cc#L203C22-L203C38
这里的
std::vector<char*> disable_fp16_ops;
是怎么管理内存的还有
FastDeploy/fastdeploy/runtime/backends/ort/ort_backend.cc
Line 255 in cc8d1f3
char* model_content_ptr
的内存是由ort 的session管理的吗?The text was updated successfully, but these errors were encountered: