diff --git a/vllm/model_executor/models/phimoe.py b/vllm/model_executor/models/phimoe.py index c8128052a3ebe..25bc0590c745c 100644 --- a/vllm/model_executor/models/phimoe.py +++ b/vllm/model_executor/models/phimoe.py @@ -38,13 +38,13 @@ from vllm.model_executor.layers.quantization.base_config import ( QuantizationConfig) from vllm.model_executor.layers.rotary_embedding import get_rope -from vllm.model_executor.layers.sampler import Sampler +from vllm.model_executor.layers.sampler import Sampler, SamplerOutput 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, maybe_remap_kv_scale_name) from vllm.model_executor.sampling_metadata import SamplingMetadata -from vllm.sequence import IntermediateTensors, SamplerOutput +from vllm.sequence import IntermediateTensors from .interfaces import SupportsLoRA