TaoLv opened a new issue #14399: [Doc] Improve the document for MKL-DNN backend URL: https://github.com/apache/incubator-mxnet/issues/14399 MKL-DNN backend is released with MXNet for several versions and in the recent 1.4.0 release we announced the brand new graph optimization feature and the INT8 quantization workflow for CPU based on MKL-DNN. With these features, users can get significant performance speedup for CPU deployment. But we also notice that there are quite a few issues about how to build and use MKL-DNN backend. So I think we should improve the document for them now, including: - [ ] - build from source on different platforms - [ ] - tutorials for quantization and accuracy tuning - [ ] - tutorials for graph optimization (operator fusion) - [ ] - performance analysis and profiling - [ ] - other faqs and tips PR list: https://github.com/apache/incubator-mxnet/pull/14202
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
