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
Add support for INT8 quantization of fusion_gru op #27330
Comments
After enabling INT8 quantization of the fusion_gru op (a PR will be submitted soon) we achieved the following accuracy result for the QAT GRU model on a CLX 6248 (with VNNI support):
|
PR #27481 submitted |
A support for INT8 quantization of the GRU model is added to Paddle. The only piece we are waiting to add here is a version of oneDNN with additional GRU INT8 optimizations. The upgrade of oneDNN will be submitted in the PR #28420. |
The PR #28420 is merged so the support for INT8 quantization of the GRU model is done. |
Please, enable INT8 quantization of the
fusion_gru
op using oneDNN-based INT8 kernel.The text was updated successfully, but these errors were encountered: