[Bugfix] Fix LoRA extra vocab size (#15047)

Signed-off-by: Jee Jee Li <[email protected]>

Author: jeejeelee

examples/offline_inference/audio_language.py

@@ -93,7 +93,6 @@ def run_phi4mm(question: str, audio_count: int) -> ModelRequestData:
         max_num_seqs=2,
         enable_lora=True,
         max_lora_rank=320,
-        lora_extra_vocab_size=0,
         limit_mm_per_prompt={"audio": audio_count},
     )
 

examples/offline_inference/vision_language.py

@@ -682,7 +682,6 @@ def run_phi4mm(questions: list[str], modality: str) -> ModelRequestData:
         max_num_seqs=2,
         enable_lora=True,
         max_lora_rank=320,
-        lora_extra_vocab_size=0,
     )
 
     return ModelRequestData(

examples/offline_inference/vision_language_multi_image.py

@@ -342,7 +342,6 @@ def load_phi4mm(question: str, image_urls: list[str]) -> ModelRequestData:
         limit_mm_per_prompt={"image": len(image_urls)},
         enable_lora=True,
         max_lora_rank=320,
-        lora_extra_vocab_size=0,
     )
 
     placeholders = "".join(f"<|image_{i}|>"

tests/models/decoder_only/vision_language/test_phi4mm.py

@@ -100,7 +100,6 @@ def run_test(
             distributed_executor_backend=distributed_executor_backend,
             enable_lora=True,
             max_lora_rank=320,
-            lora_extra_vocab_size=0,
             gpu_memory_utilization=0.8,  # set to 0.8 to avoid OOM in CI
             enforce_eager=True,
     ) as vllm_model:

vllm/config.py

@@ -2324,7 +2324,7 @@ def __post_init__(self):
         # Setting the maximum rank to 512 should be able to satisfy the vast
         # majority of applications.
         possible_max_ranks = (8, 16, 32, 64, 128, 256, 320, 512)
-        possible_lora_extra_vocab_size = (0, 256, 512)
+        possible_lora_extra_vocab_size = (256, 512)
         if self.max_lora_rank not in possible_max_ranks:
             raise ValueError(
                 f"max_lora_rank ({self.max_lora_rank}) must be one of "