Skip to content

GitLab

Unverified Commit bfab2196 authored by Jiangyun Zhu's avatar Jiangyun Zhu Committed by GitHub
Browse files

[Model] [gpt-oss] fix gpt-oss pp support (#23815) 


Signed-off-by: default avatarzjy0516 <riverclouds.zhu@qq.com>
parent a3432f18
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 3 deletions
vllm/model_executor/models/gpt_oss.py
View file @ bfab2196
...@@ -668,9 +668,8 @@ class GptOssForCausalLM(nn.Module, SupportsPP): ...@@ -668,9 +668,8 @@ class GptOssForCausalLM(nn.Module, SupportsPP):
positions: torch.Tensor, positions: torch.Tensor,
intermediate_tensors: Optional[IntermediateTensors] = None, intermediate_tensors: Optional[IntermediateTensors] = None,
inputs_embeds: Optional[torch.Tensor] = None) -> torch.Tensor: inputs_embeds: Optional[torch.Tensor] = None) -> torch.Tensor:
assert intermediate_tensors is None return self.model(input_ids, positions, intermediate_tensors,
assert inputs_embeds is None inputs_embeds)
return self.model(input_ids, positions)
def compute_logits(self, hidden_states: torch.Tensor, def compute_logits(self, hidden_states: torch.Tensor,
sampling_metadata: SamplingMetadata) -> torch.Tensor: sampling_metadata: SamplingMetadata) -> torch.Tensor:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment