You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by "rzo1 (via GitHub)" <gi...@apache.org> on 2026/10/18 12:37:44 UTC
[PR] [2.x]: GH-1390: Let SentenceVectorsDL run on a GPU (opennlp)
rzo1 opened a new pull request, #1496:
URL: https://github.com/apache/opennlp/pull/1496
Backport of #1462: SentenceVectorsDL gets a constructor that takes InferenceOptions, so it can run on a GPU like NameFinderDL and DocumentCategorizerDL. The opennlp-dl-gpu tests no longer get the CPU onnxruntime through the opennlp-dl test-jar and are skipped on macOS and aarch64. GH-1389 does not apply to 2.x, since every component creates the OrtEnvironment before adding the CUDA provider.
--
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@opennlp.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [2.x]: GH-1390: Let SentenceVectorsDL run on a GPU (opennlp)
Posted by "rzo1 (via GitHub)" <gi...@apache.org>.
rzo1 commented on PR #1496:
URL: https://github.com/apache/opennlp/pull/1496#issuecomment-6251050604
It was related to missing onnx files in the port. They are git-ignored in 2.x and need to be added by force.
--
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@opennlp.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [2.x]: GH-1390: Let SentenceVectorsDL run on a GPU (opennlp)
Posted by "krickert (via GitHub)" <gi...@apache.org>.
krickert commented on PR #1496:
URL: https://github.com/apache/opennlp/pull/1496#issuecomment-6250971773
@rzo1 if red when I get home and if it's still red, I'll retest this on cuda on linux, windoze, and see if it can nudge on an ARM NVIDIA (I test against the orin nano).
--
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@opennlp.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [2.x]: GH-1390: Let SentenceVectorsDL run on a GPU (opennlp)
Posted by "mawiesne (via GitHub)" <gi...@apache.org>.
mawiesne merged PR #1496:
URL: https://github.com/apache/opennlp/pull/1496
--
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@opennlp.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [2.x]: GH-1390: Let SentenceVectorsDL run on a GPU (opennlp)
Posted by "mawiesne (via GitHub)" <gi...@apache.org>.
mawiesne commented on PR #1496:
URL: https://github.com/apache/opennlp/pull/1496#issuecomment-6250756110
@rzo1 CI is red.
--
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@opennlp.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org