You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2019/11/08 04:58:38 UTC
[GitHub] [incubator-tvm] FrozenGene opened a new pull request #4281: Support
C++ RPC
FrozenGene opened a new pull request #4281: Support C++ RPC
URL: https://github.com/apache/incubator-tvm/pull/4281
C++ RPC is very useful for embedded devices, which can not have Python environment easily. And thanks @siju-samuel ' great work, based on https://github.com/apache/incubator-tvm/pull/1756, we could get C++ RPC work on these embedded devices. I want to summary some different places compared that PR.
- The users could only use **libtvm_runtime**, doesn't need to link libtvm. This requirement is the same as deployment.
- Previous PR could not work well and process can not exist normally. We write one method named as `waitpid_eintr` to handle it, we also modify the incorrect argument from `--timeout` to `-timeout`.
- Fix the logic of `GetCmdOption`. Previous PR can not work well like `--key=mtk6763`, which will recognize the second `k`.
- Fix the logic of `GetPath`. In our python api, we could add one argument to specify where we would like to place the deployed .so
Others small changes are not listed.
The screenshot of work example:
Device:
Server:
Better to do:
Modify the runtime code and cpp_rpc code to be C++03 compatible.
@tqchen @siju-samuel @snowolfhawk @yzhliu
----------------------------------------------------------------
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:
users@infra.apache.org
With regards,
Apache Git Services