[Chore] Remove Sampler from Model Code (#17084)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
@@ -37,7 +37,6 @@ 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 SamplerOutput, get_sampler
|
||||
from vllm.model_executor.layers.vocab_parallel_embedding import (
|
||||
ParallelLMHead, VocabParallelEmbedding)
|
||||
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
|
||||
@@ -791,7 +790,6 @@ class BartForConditionalGeneration(nn.Module, SupportsV0Only, SupportsQuant):
|
||||
|
||||
self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
|
||||
config.vocab_size)
|
||||
self.sampler = get_sampler()
|
||||
|
||||
def forward(
|
||||
self,
|
||||
@@ -828,14 +826,6 @@ class BartForConditionalGeneration(nn.Module, SupportsV0Only, SupportsQuant):
|
||||
sampling_metadata)
|
||||
return logits
|
||||
|
||||
def sample(
|
||||
self,
|
||||
logits: Optional[torch.Tensor],
|
||||
sampling_metadata: SamplingMetadata,
|
||||
) -> Optional[SamplerOutput]:
|
||||
next_tokens = self.sampler(logits, sampling_metadata)
|
||||
return next_tokens
|
||||
|
||||
stacked_params_mapping = {
|
||||
"q_proj": {
|
||||
"param_name": "qkv_proj",
|
||||
|
||||
Reference in New Issue
Block a user