You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "leandron (via GitHub)" <gi...@apache.org> on 2023/02/16 13:29:04 UTC
[GitHub] [tvm] leandron commented on a diff in pull request #14010: [TVMC][HOOKS] Target specific pre and post processing hooks
leandron commented on code in PR #14010:
URL: https://github.com/apache/tvm/pull/14010#discussion_r1108468198
##########
python/tvm/driver/tvmc/compiler.py:
##########
@@ -281,6 +299,10 @@ def compile_model(
compilation.
instruments: Optional[Sequence[PassInstrument]]
The list of pass instrument implementations.
+ pre_build_hooks: list[str], optional
+ List of pre build hooks to be applied before calling relay.build.
+ pre_build_hooks: list[str], optional
Review Comment:
```suggestion
post_build_hooks: list[str], optional
```
##########
python/tvm/driver/tvmc/composite_target.py:
##########
@@ -29,6 +29,7 @@
from tvm.relay.op.contrib.bnns import partition_for_bnns
from tvm.relay.op.contrib.vitis_ai import partition_for_vitis_ai
from tvm.relay.op.contrib.clml import partition_for_clml
+from tvm.relay.op.contrib import adreno
Review Comment:
What happens here is TVM is compiled without OpenCL support, which is the case for, example, tlcpack?
Reference: https://github.com/tlc-pack/tlcpack/blob/d3393f530331f28494b71dc68f60477e6b6dc9de/wheel/build_wheel_manylinux.sh#L88-L103
--
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