1 2 3 4 5 6 7 8
| ------------------------------ Captured log call ------------------------------- WARNING transformers.models.auto.image_processing_auto:logging.py:328 The image processor of type `Qwen2VLImageProcessor` is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with `use_fast=False`. Note that this behavior will be extended to all models in a future release.
=========================== short test summary info ============================ FAILED tests/e2e/singlecard/multi_modal/test_vl_dense_model.py::test_models_with_aclgraph[32-Qwen/Qwen2-VL-2B-Instruct] - AssertionError: Test0: vllm_eager_outputs: 'The image features a logo with two main components: the company name and a stylized graphic element. The company name is "TONGYI Qwen,"' vllm_aclgraph_outputs: 'The image features a logo with two main components: the word "TONGYI" and the word "Qwen." The word "TONGYI' ============= 1 failed, 2 passed, 8 warnings in 629.00s (0:10:29) ==============
|