You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@tvm.apache.org by Morita Kazutaka via TVM Discuss <no...@discuss.tvm.ai> on 2020/07/01 01:31:09 UTC

[TVM Discuss] [Development/RFC] [RFC][BYOC] Runtime module to offload subgraph to edge server


@zhiics Thanks for your comment.  Yes, I just use BYOC to specify which part should be offloaded.  The subgraph can be a blackbox for users.

There are two ways I tried to prepare the package.

1. Cross-compile locally and upload the built lib to the remote server. [[code](https://github.com/kazum/tvm/blob/remote_runtime/apps/ios_rpc/tests/ios_rpc_maskrcnn.py#L168)]

   This works if we know the content of the subgraph and we have a toolchain to cross-compile it.

2. Build the subgraph manually on the remote server.

   Here is a [script](https://github.com/kazum/tvm/blob/remote_runtime/apps/ios_rpc/tests/mask_rcnn_build_heads.py) I used to build the remote package with CUDA. Currently, the file name of the deployed package depends on the symbol name produced by BYOC, so I have to manually specify it in the script for now.





---
[Visit Topic](https://discuss.tvm.ai/t/rfc-byoc-runtime-module-to-offload-subgraph-to-edge-server/7141/3) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/283f6a0e6fb8db84df5b5832e6799545c7c18e3aa64bbf462ec1decb7b9fc8c1).