Move`VllmConfig` from `config/__init__.py` to `config/vllm.py` (#25271)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/model_executor/models/bailing_moe.py

@@ -45,8 +45,7 @@ from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
                                                QKVParallelLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     ParallelLMHead, VocabParallelEmbedding)

vllm/model_executor/models/granite.py

@@ -41,8 +41,7 @@ from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
                                                QKVParallelLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)

vllm/model_executor/models/granitemoe.py

@@ -42,8 +42,7 @@ from vllm.model_executor.layers.linear import (QKVParallelLinear,
                                                ReplicatedLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)

vllm/model_executor/models/granitemoeshared.py

@@ -21,8 +21,7 @@ from vllm.model_executor.layers.layernorm import RMSNorm
 from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
 from vllm.sequence import IntermediateTensors

vllm/model_executor/models/hunyuan_v1.py

@@ -47,8 +47,7 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                ReplicatedLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)

vllm/model_executor/models/interfaces.py

@@ -16,8 +16,7 @@ from vllm.config import ModelConfig, SpeechToTextConfig
 from vllm.inputs import TokensPrompt
 from vllm.inputs.data import PromptType
 from vllm.logger import init_logger
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.utils import supports_kw
 
 from .interfaces_base import VllmModel, is_pooling_model

vllm/model_executor/models/llama4_eagle.py

@@ -28,8 +28,7 @@ from vllm.distributed.parallel_state import get_pp_group
 from vllm.logger import init_logger
 from vllm.model_executor.layers.layernorm import RMSNorm
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.quantization.torchao import TorchAOConfig
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     VocabParallelEmbedding)

vllm/model_executor/models/mamba.py

@@ -16,8 +16,7 @@ from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.mamba.mamba_mixer import MambaMixer
 from vllm.model_executor.layers.mamba.mamba_utils import (
     MambaStateDtypeCalculator, MambaStateShapeCalculator)
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader

vllm/model_executor/models/mamba2.py

@@ -16,8 +16,7 @@ from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.mamba.mamba_mixer2 import MambaMixer2
 from vllm.model_executor.layers.mamba.mamba_utils import (
     MambaStateDtypeCalculator, MambaStateShapeCalculator)
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader

vllm/model_executor/models/minimax_text_01.py

@@ -33,8 +33,7 @@ from vllm.model_executor.layers.mamba.linear_attn import (
     MiniMaxText01LinearAttention)
 from vllm.model_executor.layers.mamba.mamba_utils import (
     MambaStateDtypeCalculator, MambaStateShapeCalculator)
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)

vllm/model_executor/models/ovis.py

@@ -29,8 +29,7 @@ from transformers import BatchFeature, PretrainedConfig
 
 from vllm.config import VllmConfig
 from vllm.model_executor.layers.linear import ReplicatedLinear
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.models.aimv2 import AIMv2Model
 from vllm.model_executor.models.siglip import SiglipVisionModel
 from vllm.model_executor.models.utils import (AutoWeightsLoader, flatten_bn,

vllm/model_executor/models/ovis2_5.py

@@ -11,8 +11,7 @@ from transformers import BaseImageProcessor, BatchFeature, PretrainedConfig
 
 from vllm.config import VllmConfig
 from vllm.model_executor.layers.linear import ReplicatedLinear
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.models.ovis import (OvisImagePatchInputs,
                                              VisualEmbedding)
 from vllm.model_executor.models.siglip2navit import Siglip2NavitModel

vllm/model_executor/models/phimoe.py

@@ -40,8 +40,7 @@ from vllm.model_executor.layers.linear import (QKVParallelLinear,
                                                ReplicatedLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)

vllm/model_executor/models/siglip2navit.py

@@ -14,13 +14,13 @@ from transformers import Siglip2VisionConfig
 from transformers.configuration_utils import PretrainedConfig
 
 from vllm.attention.layer import check_upstream_fa_availability
-from vllm.config import QuantizationConfig
 from vllm.distributed import divide, get_tensor_model_parallel_world_size
 from vllm.model_executor.layers.activation import get_act_fn
 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                LinearBase, QKVParallelLinear,
                                                ReplicatedLinear,
                                                RowParallelLinear)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
 from vllm.platforms import _Backend
 

vllm/model_executor/models/step3_text.py

@@ -23,8 +23,7 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                ReplicatedLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)

vllm/model_executor/models/whisper.py

@@ -26,8 +26,7 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                QKVParallelLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.quantization.base_config import (
-    QuantizationConfig)
+from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
 from vllm.model_executor.model_loader.utils import set_default_torch_dtype
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader