samskalicky commented on pull request #19112: URL: https://github.com/apache/incubator-mxnet/pull/19112#issuecomment-691362743
@hahtk ive added support for specifying `dedup_subgraph=True` to `optimize_for` to enable subgraph input/output deduplication for our usage. This will allow us to move forward in parallel while we work with the Intel folks to incorporate the improvement for MKLDNN later. ---------------------------------------------------------------- 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]
