Fix regression tests on CUDA and ROCm

[jakki-amd]

Fix regression tests

[eppane]

Appended the comment in pull request #5:

OBS! The test test_handler.py::test_huggingface_bert_model_parallel_inference fails due to:

ValueError: Input length of input_ids is 150, but max_length is set to 50. This can lead to unexpected behavior. You should consider increasing max_length or, better yet, setting max_new_tokens.

This indicates that preprocessing uses a different max_length than inference, which can be verified when looking at the handler when the test was originally implemented: model.generate() has max_length=50 by default, while tokenizer uses max_length from setup_config (max_length=150). It seems that the bert-based Textgeneration.mar needs an update.