Skip to content
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

bugfix/trt op with kernel #11408

Closed

Conversation

Superjomn
Copy link
Contributor

@Superjomn Superjomn commented Jun 12, 2018

  • add one FC layer for benchmark
  • TODO add more layers
  • fixed a bug, about not share the TRT engine for all the TRT engine op kernels.

@Superjomn Superjomn changed the title Feature/trt manul benchmark bugfix/trt op with kernel Jun 14, 2018
return engines_.at(name).get();
}

// Create or get an engine called `key`
Copy link
Contributor

Choose a reason for hiding this comment

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

Create an engine called name

mutable inference::tensorrt::TensorRTEngine* engine_{nullptr};
mutable int max_batch_{0};
// TODO(Superjomn) replace this stream with context's stream.
// mutable cudaStream_t stream_;
Copy link
Contributor

Choose a reason for hiding this comment

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

原来声明的stream_,engine_, max_batch_都不要了?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

对,之前那些会出现 bug:kernel 每个 type 全局只有一份,所以不能有 member。

@CLAassistant

This comment has been minimized.

@Superjomn Superjomn self-assigned this Jun 14, 2018
@Superjomn Superjomn closed this Jun 14, 2018
@Superjomn Superjomn mentioned this pull request Jun 14, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants