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 2021/11/09 23:49:03 UTC

[GitHub] [tvm] areusch commented on a change in pull request #9229: [TVMC][microTVM] Add new micro context

areusch commented on a change in pull request #9229:
URL: https://github.com/apache/tvm/pull/9229#discussion_r746137979



##########
File path: python/tvm/driver/tvmc/common.py
##########
@@ -38,6 +41,36 @@
 class TVMCException(Exception):
     """TVMC Exception"""
 
+class TVMCSilentArgumentParser(argparse.ArgumentParser):

Review comment:
       just curious: was there a reason we couldn't use `add_help=False` for each TVMC ArgumentParser, and then manually add it ourselves at the last minute? this approach requires us to use `_remove_action`, which is marked private.

##########
File path: include/tvm/runtime/device_api.h
##########
@@ -268,6 +268,8 @@ inline const char* DeviceName(int type) {
       return "webgpu";
     case kDLHexagon:
       return "hexagon";
+    case 129:

Review comment:
       so this is an RPC device ID. you shouldn't need to define this, and we can't submit this chance to device_api.h (only DeviceType enums should be here

##########
File path: include/tvm/runtime/device_api.h
##########
@@ -268,6 +268,8 @@ inline const char* DeviceName(int type) {
       return "webgpu";
     case kDLHexagon:
       return "hexagon";
+    case 129:

Review comment:
       so this is an RPC device ID. you shouldn't need to define this, and we can't submit this change to device_api.h (only DeviceType enums should be here




-- 
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