This is an automated email from the ASF dual-hosted git repository.
krickert pushed a change to branch OPENNLP-1982-embed-padding
in repository https://gitbox.apache.org/repos/asf/opennlp.git
was 8c7c439df GH-1392: Pad to the longest text by default on a GPU
This change permanently discards the following revisions:
discard 8c7c439df GH-1392: Pad to the longest text by default on a GPU
discard 8c1bc0759 GH-1392: Add padding strategies for embedAll
discard 82156b04f GH-1391: Share the batch test fixtures and drop duplicate
tests
discard 8592377fb GH-1391: Test the batch boundaries and split groups of
embedAll
discard 6557e4c4d GH-1391: Shorten the embedAll Javadoc and compute the
expected batch sizes
discard cd2fbba3c GH-1391: Cap the token positions of one embedAll inference
discard bcdd68d90 GH-1391: Test that embedAll caps the token positions of one
inference
discard 8d4e792d1 GH-1389: Share the tiny model test fixtures
discard 99d88ba09 GH-1389: Skip the opennlp-dl-gpu tests where onnxruntime_gpu
has no native library
discard 576206d29 GH-1389, GH-1390: Let SentenceVectorsDL run on a GPU and fix
the first CUDA request in a fresh JVM
