diff --git a/vllm/lora/model_manager.py b/vllm/lora/model_manager.py
index b948f1d66..7611d2d71 100644
--- a/vllm/lora/model_manager.py
+++ b/vllm/lora/model_manager.py
@@ -35,7 +35,7 @@ from vllm.model_executor.models.interfaces import is_pooling_model
 from vllm.model_executor.models.module_mapping import MultiModelKeys
 from vllm.model_executor.models.utils import PPMissingLayer
 from vllm.multimodal import MULTIMODAL_REGISTRY
-from vllm.multimodal.budget import MultiModalBudget
+from vllm.multimodal.encoder_budget import MultiModalBudget
 from vllm.utils.cache import LRUCache
 from vllm.utils.platform_utils import is_pin_memory_available
 
diff --git a/vllm/multimodal/budget.py b/vllm/multimodal/encoder_budget.py
similarity index 100%
rename from vllm/multimodal/budget.py
rename to vllm/multimodal/encoder_budget.py
diff --git a/vllm/v1/core/sched/scheduler.py b/vllm/v1/core/sched/scheduler.py
index 0b8832c16..90ca58441 100644
--- a/vllm/v1/core/sched/scheduler.py
+++ b/vllm/v1/core/sched/scheduler.py
@@ -31,7 +31,7 @@ from vllm.model_executor.layers.fused_moe.routed_experts_capturer import (
     RoutedExpertsReader,
 )
 from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
-from vllm.multimodal.budget import MultiModalBudget
+from vllm.multimodal.encoder_budget import MultiModalBudget
 from vllm.v1.core.encoder_cache_manager import (
     EncoderCacheManager,
     EncoderDecoderCacheManager,
diff --git a/vllm/v1/engine/input_processor.py b/vllm/v1/engine/input_processor.py
index 98c3a07d1..47180ee59 100644
--- a/vllm/v1/engine/input_processor.py
+++ b/vllm/v1/engine/input_processor.py
@@ -18,7 +18,7 @@ from vllm.inputs.preprocess import InputPreprocessor
 from vllm.logger import init_logger
 from vllm.lora.request import LoRARequest
 from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
-from vllm.multimodal.budget import MultiModalBudget
+from vllm.multimodal.encoder_budget import MultiModalBudget
 from vllm.multimodal.inputs import (
     MultiModalDataDict,
     MultiModalFeatureSpec,
diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
index 1dbf96090..a7c2a8800 100644
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
@@ -82,7 +82,7 @@ from vllm.model_executor.models.interfaces_base import (
     is_text_generation_model,
 )
 from vllm.multimodal import MULTIMODAL_REGISTRY
-from vllm.multimodal.budget import MultiModalBudget
+from vllm.multimodal.encoder_budget import MultiModalBudget
 from vllm.multimodal.inputs import (
     BatchedTensorInputs,
     MultiModalKwargsItem,