biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 Deprecation] Remove V0 sampling metadata (#25345)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
This commit is contained in:
Woosuk Kwon
2025-09-21 10:37:11 -07:00
committed by GitHub
parent c438b2951c
commit 1c3ffdbecc
141 changed files with 172 additions and 583 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/model_executor/models/minimax_text_01.py
View File

@@ -41,7 +41,6 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.models.utils import maybe_prefix
from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors
from .interfaces import HasInnerState, IsHybrid
@@ -742,10 +741,8 @@ class MiniMaxText01ForCausalLM(nn.Module, HasInnerState, IsHybrid):
return hidden_states
def compute_logits(self, hidden_states: torch.Tensor,
sampling_metadata: SamplingMetadata) -> torch.Tensor:
logits = self.logits_processor(self.lm_head, hidden_states.float(),
sampling_metadata)
def compute_logits(self, hidden_states: torch.Tensor) -> torch.Tensor:
logits = self.logits_processor(self.lm_head, hidden_states.float())
return logits