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 2022/02/25 12:44:05 UTC

[GitHub] [tvm] manupa-arm commented on a change in pull request #10377: [microNPU][6] Migrate codegen to use cascader

manupa-arm commented on a change in pull request #10377:
URL: https://github.com/apache/tvm/pull/10377#discussion_r814737767



##########
File path: python/tvm/relay/backend/contrib/ethosu/codegen.py
##########
@@ -336,7 +379,10 @@ def relay_to_tir_func(ext_func: relay.Function) -> tvm.tir.PrimFunc:
     # this should be a single intelligent and a composite scheduler
     # that can perform scheduling based on user inputs such as
     # scratch memory size.
-    tir_mod, const_dict = lower_to_tir(mod["main"], copy_constants())
+    try:

Review comment:
       I think we should use relay.ext.ethos-u.options either to explicitly enable or explicitly disable the cascader.
   If we think, if the feature is not stable enough, we could try a explicit enable.
   
   Once it get matures, we could make that the default. 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