krickert commented on code in PR #1462:
URL: https://github.com/apache/opennlp/pull/1462#discussion_r4242594901
##########
opennlp-core/opennlp-ml/opennlp-dl-gpu/pom.xml:
##########
@@ -102,5 +109,31 @@
</plugins>
</build>
+ <!-- onnxruntime_gpu ships native libraries for linux-x64 and win-x64 only.
-->
+ <profiles>
+ <profile>
+ <id>no-onnxruntime-gpu-on-mac</id>
+ <activation>
+ <os>
+ <family>mac</family>
+ </os>
+ </activation>
+ <properties>
+ <skipTests>true</skipTests>
+ </properties>
+ </profile>
+ <profile>
+ <id>no-onnxruntime-gpu-on-aarch64</id>
Review Comment:
No problem. I'm also going to make an addon for poor 'ole OSX too that
won't use ONNX :) It's far faster and superior to just use the apple metal APIs
than ONNX (OSX on ONNX isn't that good as of today). But since we made this
generic (go us!) it'll just need to be included at runtime. Out of scope for
now - but relevant to quickly mention to you.
--
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]
