[BugFix] Fix test breakages from transformers 4.45 upgrade

tests/models/decoder_only/vision_language/test_llava_onevision.py

@@ -259,6 +259,7 @@ def run_image_test(
     # max_model_len should be greater than image_feature_size
     with vllm_runner(model,
                      dtype=dtype,
+                     max_num_seqs=1,
                      max_model_len=32768,
                      tensor_parallel_size=tensor_parallel_size,
                      distributed_executor_backend=distributed_executor_backend,

tests/samplers/test_sampler.py

@@ -596,8 +596,12 @@ def test_sampler_top_k_top_p(seed: int, device: str):
     generation_config = GenerationConfig(top_k=top_k,
                                          top_p=top_p,
                                          do_sample=True)
-    warpers = generation_model._get_logits_warper(generation_config, device)
-    assert len(warpers) == 2  # top_p and top_k
+    processors = generation_model._get_logits_processor(generation_config,
+                                                        None,
+                                                        None,
+                                                        None, [],
+                                                        device=device)
+    assert len(processors) == 2  # top_p and top_k
 
     seq_group_metadata_list: List[SequenceGroupMetadata] = []
     seq_lens: List[int] = []
@@ -639,7 +643,7 @@ def mock_sample(probs, *args, **kwargs):
 
     assert sample_probs is not None
 
-    hf_probs = warpers(torch.zeros_like(fake_logits), fake_logits.clone())
+    hf_probs = processors(torch.zeros_like(fake_logits), fake_logits.clone())
     hf_probs = torch.softmax(hf_probs, dim=-1, dtype=torch.float)
     torch.testing.assert_close(hf_probs, sample_probs, rtol=0.0, atol=1e-5)
     assert torch.equal(hf_probs.eq(0), sample_probs.eq(0))

vllm/config.py

@@ -1740,7 +1740,7 @@ def _get_and_verify_max_len(
                     "with rope_scaling. Please raise an issue so we can "
                     "investigate.")
 
-            if rope_type == "mrope":
+            if rope_type in ("mrope", "default"):
                 scaling_factor = 1
             else:
                 assert "factor" in rope_scaling

vllm/transformers_utils/tokenizer.py

@@ -167,7 +167,7 @@ def get_lora_tokenizer(lora_request: LoRARequest, *args,
         return None
     try:
         tokenizer = get_tokenizer(lora_request.lora_path, *args, **kwargs)
-    except OSError as e:
+    except (OSError, ValueError) as e:
         # No tokenizer was found in the LoRA folder,
         # use base model tokenizer
         logger.warning(