[Chore] Remove unused sampler in models (#25324)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-09-20 19:53:20 -07:00
committed by GitHub
parent 86647d1cd0
commit 572ddf83ce
5 changed files with 0 additions and 49 deletions
-10
View File
@@ -41,7 +41,6 @@ from vllm.model_executor.layers.mamba.ops.ssd_combined import (
mamba_chunk_scan_combined)
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
from vllm.model_executor.layers.vocab_parallel_embedding import (
DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
from vllm.model_executor.model_loader.weight_utils import (
@@ -932,7 +931,6 @@ class Plamo2ForCausalLM(torch.nn.Module, HasInnerState, SupportsPP, IsHybrid):
self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
self.config.vocab_size)
self.sampler = get_sampler()
self.make_empty_intermediate_tensors = (
self.model.make_empty_intermediate_tensors)
@@ -1030,14 +1028,6 @@ class Plamo2ForCausalLM(torch.nn.Module, HasInnerState, SupportsPP, IsHybrid):
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
def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]):
params_dict = dict(self.named_parameters())
for name, loaded_weight in weights: