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 2022/08/26 09:30:24 UTC

[GitHub] [tvm] alter-xp commented on pull request #12614: [BYOC] Integrate CSI-NN2 and add unit test for Conv2D

alter-xp commented on PR #12614:
URL: https://github.com/apache/tvm/pull/12614#issuecomment-1228275828

   Hi @areusch , when integrating csinn2, I have encountered some CI problems. Could you give me some advice?
   1. [Test docs: GPU] always tries to run the case file added for D1 [gallery/how_to/deploy_models/deploy_model_on_d1.py]. This file cannot run without compiling TVM with csinn x86 runtime.
   2. The unit test added for riscv seems to be run by multiple backend
   3. For csinn2, I need to build two contents. One is build for x86 [tests/scripts/task_config_build_csinn2.sh] . At this time, I need to compile the entire TVM, while build for c906 [tests/scripts/task_config_build_c906.sh ] only needs to compile the tvm_rpc. The unit test depend on this tvm_rpc.
   To be honest, these questions took me a lot of time. It would be great if you could give me some advice.
    Thanks !


-- 
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: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org