You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "mehrdadh (via GitHub)" <gi...@apache.org> on 2023/02/22 21:53:25 UTC

[GitHub] [tvm] mehrdadh commented on a diff in pull request #14077: [Draft][microTVM]Enable TVMC micro with AoT Executor

mehrdadh commented on code in PR #14077:
URL: https://github.com/apache/tvm/pull/14077#discussion_r1115003967


##########
gallery/how_to/work_with_microtvm/micro_tvmc.sh:
##########
@@ -126,7 +124,7 @@ tvmc micro create \
     project \
     model.tar \
     zephyr \
-    --project-option project_type=host_driven zephyr_board=qemu_x86
+    --project-option project_type=host_driven board=qemu_x86
 # bash
 # This will generate a ``Host-Driven`` Zephyr project for ``qemu_x86`` Zephyr board. In Host-Driven template project,
 # the Graph Executor will run on host and perform the model execution on Zephyr device by issuing commands to the

Review Comment:
   I think ideally the default for `tvmc compile` for `micro` should be using AoT executor. Graph Executor is becoming less important, specially for micro devices, as we improved AoT flow, so I suggest to just briefly mention the options.
   
   Regarding the default AoT flow for `tvm compile` for micro devices, I haven't found a way yet. One possible way it to set it based on the runtime=crt. wdyt? 



-- 
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