[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
@@ -33,7 +33,6 @@ from vllm.config import CacheConfig, ModelConfig, VllmConfig
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.logits_processor import LogitsProcessor
from vllm.model_executor.layers.quantization 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
@@ -160,7 +159,6 @@ class ErnieMTP(nn.Module, SupportsPP):
self.lm_head = ParallelLMHead(self.config.vocab_size,
self.config.hidden_size,
prefix=maybe_prefix(prefix, "lm_head"))
self.sampler = get_sampler()
if self.config.tie_word_embeddings:
self.lm_head.weight = self.model.embed_tokens.weight
@@ -188,14 +186,6 @@ class ErnieMTP(nn.Module, SupportsPP):
return self.model.compute_logits(hidden_states, self.lm_head,
sampling_metadata, spec_step_idx)
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]:
stacked_params_mapping = [