[Chore] Remove Sampler from Model Code (#17084)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
@@ -21,7 +21,6 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
|
||||
from vllm.model_executor.layers.logits_processor import LogitsProcessor
|
||||
from vllm.model_executor.layers.quantization.base_config import (
|
||||
QuantizationConfig)
|
||||
from vllm.model_executor.layers.sampler import Sampler, SamplerOutput
|
||||
from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
|
||||
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
|
||||
from vllm.model_executor.sampling_metadata import SamplingMetadata
|
||||
@@ -669,7 +668,6 @@ class WhisperForConditionalGeneration(nn.Module, SupportsTranscription,
|
||||
logit_scale = getattr(config, "logit_scale", 1.0)
|
||||
self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
|
||||
config.vocab_size, logit_scale)
|
||||
self.sampler = Sampler()
|
||||
|
||||
def forward(
|
||||
self,
|
||||
@@ -724,14 +722,6 @@ class WhisperForConditionalGeneration(nn.Module, SupportsTranscription,
|
||||
sampling_metadata)
|
||||
return logits
|
||||
|
||||
def sample(
|
||||
self,
|
||||
logits: torch.Tensor,
|
||||
sampling_metadata: SamplingMetadata,
|
||||
) -> Optional[SamplerOutput]:
|
||||
next_tokens = self.sampler(logits, sampling_metadata)
|
||||
return next_tokens
|
||||
|
||||
def load_weights(self, weights: Iterable[Tuple[str,
|
||||
torch.Tensor]]) -> Set[str]:
|
||||
loader = AutoWeightsLoader(self, skip_prefixes=["proj_out."])
|
||||
|
||||
Reference in New Issue
Block a user