[Model] Remove model sampler (#21059)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -23,7 +23,6 @@ from vllm.model_executor.layers.mamba.ops.causal_conv1d import (
|
||||
causal_conv1d_fn, causal_conv1d_update)
|
||||
from vllm.model_executor.layers.mamba.ops.mamba_ssm import (
|
||||
selective_scan_fn, selective_state_update)
|
||||
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.models.interfaces import (HasInnerState, IsHybrid,
|
||||
@@ -641,7 +640,6 @@ class Phi4FlashForCausalLM(nn.Module, HasInnerState, IsHybrid, SupportsV0Only):
|
||||
self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
|
||||
config.vocab_size,
|
||||
logits_as_input=False)
|
||||
self.sampler = get_sampler()
|
||||
|
||||
def forward(
|
||||
self,
|
||||
@@ -709,14 +707,6 @@ class Phi4FlashForCausalLM(nn.Module, HasInnerState, IsHybrid, SupportsV0Only):
|
||||
prune_hidden_states=prune_hidden_states)
|
||||
return processed_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]],
|
||||
|
||||
Reference in New Issue
Block a user