[Qwen4Exp] Repair: import Qwen4ExpTextConfig from transformers

Upstream e3cae8d2ac (#57387) deleted vllm/transformers_utils/configs/
qwen4_exp.py and moved the config family into the model package, so
that module path no longer resolves. transformers 5.18 exports the
config itself, which is how the rest of this fork imports it
(nvidia/model.py, amd/mtp.py, and nvidia/qsa.py at the base).

vllm/models/qwen4_exp/common/mtp.py carried the dead path at the base,
which made the Qwen4Exp model package fail to import at all; the PLE
pull transport and the FP8-KV reader added two more users of it.

Co-Authored-By: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>

vllm/models/qwen4_exp/common/mtp.py

@@ -5,7 +5,7 @@
 import torch
 
 from vllm.config import VllmConfig
-from vllm.transformers_utils.configs.qwen4_exp import Qwen4ExpTextConfig
+from transformers import Qwen4ExpTextConfig
 
 
 def make_mtp_hidden_buffer(

vllm/models/qwen4_exp/nvidia/ple_pull.py

@@ -35,7 +35,7 @@ from vllm.model_executor.layers.ple_offload_layer import (
     is_offload_process,
 )
 from vllm.model_executor.layers.quantization.base_config import QuantizationConfig
-from vllm.transformers_utils.configs.qwen4_exp import Qwen4ExpTextConfig
+from transformers import Qwen4ExpTextConfig
 
 from .ngram_embedding import (
     Qwen4ExpNGramEmbedding,

vllm/models/qwen4_exp/nvidia/qsa.py

@@ -40,9 +40,6 @@ from vllm.model_executor.models.qwen3_next import Qwen3NextAttention
 from vllm.model_executor.models.utils import AutoWeightsLoader, WeightsMapper
 from vllm.platforms import current_platform
 from vllm.platforms.interface import DeviceCapability
-from vllm.transformers_utils.configs.qwen4_exp import (
-    Qwen4ExpTextConfig,
-)
 from vllm.utils.torch_utils import (
     LayerNameType,
     _encode_layer_name,