[Core] Refactor model loading code (#4097)
This commit is contained in:
@@ -6,7 +6,7 @@ from vllm.config import (DeviceConfig, ModelConfig, ParallelConfig,
|
||||
SchedulerConfig)
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor import SamplingMetadata
|
||||
from vllm.model_executor.neuron_model_loader import get_neuron_model
|
||||
from vllm.model_executor.model_loader.neuron import get_neuron_model
|
||||
from vllm.sampling_params import SamplingParams, SamplingType
|
||||
from vllm.sequence import SamplerOutput, SequenceData, SequenceGroupMetadata
|
||||
from vllm.utils import (async_tensor_h2d, is_pin_memory_available,
|
||||
|
||||
Reference in New Issue
Block a user