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

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-03-13 20:49:08 +00:00
parent d0b402974f
commit 0005d2a3c9
7 changed files with 162 additions and 89 deletions
--- a/tests/models/multimodal/generation/test_common.py
+++ b/tests/models/multimodal/generation/test_common.py
@@ -206,9 +206,7 @@ VLM_TEST_SETTINGS = {
            "model_impl": "transformers",
            "default_torch_num_threads": 1,
        },
-        # FIXME: Investigate why the test hangs
-        # when processing the 3rd prompt in vLLM
-        marks=[pytest.mark.core_model, pytest.mark.skip(reason="Test hangs")],
+        marks=[pytest.mark.core_model],
    ),
    # Gemma3 has bidirectional mask on images
    "gemma3-transformers": VLMTestInfo(