areusch commented on a change in pull request #5921:
URL: https://github.com/apache/incubator-tvm/pull/5921#discussion_r451847555
##########
File path: apps/bundle_deploy/build_model.py
##########
@@ -33,19 +34,21 @@ def build_module(opts):
func = mod["main"]
func = relay.Function(func.params, relay.nn.softmax(func.body), None,
func.type_params, func.attrs)
- with tvm.transform.PassContext(opt_level=3):
+ with tvm.transform.PassContext(opt_level=3,
config={'tir.disable_vectorize': True}):
graph, lib, params = relay.build(
- func, 'llvm --system-lib', params=params)
+ func, 'c', params=params)
Review comment:
llvm didn't work on my mac, but I can leave this alone at HEAD if it
works for others.
--system-lib is being handled differently now (I.e. by
`python/tvm/micro/function_registry.py`) but should be able to fold that in to
C++ (I.e. as something like `--system-lib --runtime=crt`) in a follow-on.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
