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 16, 17:00 UTC
[Bugfix] Fix import error in Exaone model (#8034)
Cyrus Leung committed
Aug 30, 2024 at 23:03 UTC
afd39a4511111aa05fd58834191d46328aed5a27
1 file changed
+2
-2
vllm/model_executor/models/exaone.py
+2
-2
@@ -43,13 +43,13 @@ from vllm.model_executor.layers.quantization.base_config import (
43
from vllm.model_executor.layers.quantization.compressed_tensors.utils import (
44
get_compressed_tensors_cache_scale)
45
from vllm.model_executor.layers.rotary_embedding import get_rope
46
-from vllm.model_executor.layers.sampler import Sampler
46
+from vllm.model_executor.layers.sampler import Sampler, SamplerOutput
47
from vllm.model_executor.layers.vocab_parallel_embedding import (
48
DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
49
from vllm.model_executor.model_loader.weight_utils import (
50
default_weight_loader, kv_cache_scales_loader, maybe_remap_kv_scale_name)
51
from vllm.model_executor.sampling_metadata import SamplingMetadata
52
-from vllm.sequence import IntermediateTensors, SamplerOutput
52
+from vllm.sequence import IntermediateTensors
53
from vllm.transformers_utils.configs.exaone import ExaoneConfig
54
from vllm.utils import is_hip
55