Andreas KaratzasandGitHub 0d50fa1db6 [ROCm][CI] Mark gemma3 as large GPU test to avoid OOM on MI250 (#37610) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

2026-03-21 12:57:25 +08:00

..

generation

[ROCm][CI] Mark gemma3 as large GPU test to avoid OOM on MI250 (#37610)

2026-03-21 12:57:25 +08:00

pooling

[ROCm][CI] Fix accuracy for llama-nemotron-vl pooling tests (#37613)

2026-03-20 10:16:59 -07:00

processing

[Model] Remove unused handle_oov_mm_token (#37321)

2026-03-17 19:44:52 +00:00

__init__.py

[CI/Build] Move model-specific multi-modal processing tests (#11934)

2025-01-11 13:50:05 +08:00

conftest.py

[ROCm][CI] Disable skinny GEMMs in multimodal tests to fix non-deterministic results (#35049)

2026-02-25 16:48:37 +00:00

test_mapping.py

Use Transformers v5 WeightRenaming for Transformers modeling backend (#31545)

2026-03-13 20:49:08 +00:00