leandron commented on code in PR #14077:
URL: https://github.com/apache/tvm/pull/14077#discussion_r1114355493
##########
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 some other parts of the tutorial need to be reviewed as we move from
Graph to AoT. I'd also recommend clarifying which one we recommend, which in
this case I assume is AoT, but then describe why in the tutorial would be good.
##########
python/tvm/driver/tvmc/model.py:
##########
@@ -407,6 +407,12 @@ def import_package(self, package_path: str):
params = temp.relpath(f"parameters/{module_name}.params")
self.type = "mlf"
+
+ # Set executor type
+ if len(metadata["modules"]["default"]["executors"]) > 1:
+ raise TVMCException("Module with only one executor type is
supported.")
Review Comment:
Can this message be made a bit more clear and perhaps suggest the user what
do to, or at least show which executor types were found?
--
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]
