[
https://issues.apache.org/jira/browse/OPENNLP-1982?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18125460#comment-18125460
]
ASF GitHub Bot commented on OPENNLP-1982:
-----------------------------------------
mawiesne commented on code in PR #1462:
URL: https://github.com/apache/opennlp/pull/1462#discussion_r4228727121
##########
opennlp-core/opennlp-ml/opennlp-dl/src/test/java/opennlp/dl/ColdStartCudaProbe.java:
##########
@@ -37,6 +37,12 @@ public final class ColdStartCudaProbe {
private ColdStartCudaProbe() {
}
+ /**
+ * Requests the CUDA execution provider for device {@code 0} and prints
{@link #ADDED} or
+ * {@link #REJECTED} followed by the ONNX Runtime error.
+ *
+ * @param args Not used.
+ */
public static void main(String[] args) {
Review Comment:
Do we need this one here? pls check / remove main.
> SentenceVectorsDL cannot run on a GPU
> -------------------------------------
>
> Key: OPENNLP-1982
> URL: https://issues.apache.org/jira/browse/OPENNLP-1982
> Project: OpenNLP
> Issue Type: Bug
> Affects Versions: 2.5.12, 3.0.0-M6
> Reporter: Richard Zowalla
> Assignee: Kristian Rickert
> Priority: Minor
> Fix For: 3.0.0
>
>
> {{SentenceVectorsDL}} always creates default {{OrtSession.SessionOptions}},
> so unlike {{NameFinderDL}} and {{DocumentCategorizerDL}} it cannot use the
> CUDA execution provider through {{InferenceOptions}}. Add a constructor that
> takes {{InferenceOptions}} and, once OPENNLP\-1937 is in, expose the device
> \(e.g. {{cpu}} / {{cuda:N}}\), a maximum batch size and the intra\-op thread
> count as options of the ONNX text embedder provider.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
