crazydemo opened a new pull request #10835: URL: https://github.com/apache/tvm/pull/10835
This PR is inspired by `tensorrt.py`. It aims to add `prune` function to `dnnl subgraphs`, so that we can only keep partitions contain compute-intensive ops, and offload some useless partitions from dnnl codegen. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
