A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 16:30 UTC
[Tiny] Rename encoder budget file to more specific name (#34103)
Signed-off-by: Reagan Lee <“reaganjlee@gmail.com”> Co-authored-by: Reagan Lee <“reaganjlee@gmail.com”>
Reagan Lee committed
Feb 8, 2026 at 19:48 UTC
7c233dbb36262b5106f46eb21a6324d15e424005
5 files changed
+4
-4
vllm/lora/model_manager.py
+1
-1
@@ -35,7 +35,7 @@ from vllm.model_executor.models.interfaces import is_pooling_model
35
from vllm.model_executor.models.module_mapping import MultiModelKeys
36
from vllm.model_executor.models.utils import PPMissingLayer
37
from vllm.multimodal import MULTIMODAL_REGISTRY
38
-from vllm.multimodal.budget import MultiModalBudget
38
+from vllm.multimodal.encoder_budget import MultiModalBudget
39
from vllm.utils.cache import LRUCache
40
from vllm.utils.platform_utils import is_pin_memory_available
41
vllm/multimodal/encoder_budget.py
renamed
vllm/v1/core/sched/scheduler.py
+1
-1
@@ -31,7 +31,7 @@ from vllm.model_executor.layers.fused_moe.routed_experts_capturer import (
31
RoutedExpertsReader,
32
)
33
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
34
-from vllm.multimodal.budget import MultiModalBudget
34
+from vllm.multimodal.encoder_budget import MultiModalBudget
35
from vllm.v1.core.encoder_cache_manager import (
36
EncoderCacheManager,
37
EncoderDecoderCacheManager,
vllm/v1/engine/input_processor.py
+1
-1
@@ -18,7 +18,7 @@ from vllm.inputs.preprocess import InputPreprocessor
18
from vllm.logger import init_logger
19
from vllm.lora.request import LoRARequest
20
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
21
-from vllm.multimodal.budget import MultiModalBudget
21
+from vllm.multimodal.encoder_budget import MultiModalBudget
22
from vllm.multimodal.inputs import (
23
MultiModalDataDict,
24
MultiModalFeatureSpec,
vllm/v1/worker/gpu_model_runner.py
+1
-1
@@ -82,7 +82,7 @@ from vllm.model_executor.models.interfaces_base import (
82
is_text_generation_model,
83
)
84
from vllm.multimodal import MULTIMODAL_REGISTRY
85
-from vllm.multimodal.budget import MultiModalBudget
85
+from vllm.multimodal.encoder_budget import MultiModalBudget
86
from vllm.multimodal.inputs import (
87
BatchedTensorInputs,
88
MultiModalKwargsItem,