Skip to content

GitLab

Unverified Commit 838d7116 authored by Icey's avatar Icey Committed by GitHub
Browse files

[Qwen] Remove cuda hard-code in qwen3 next (#25243) 


Signed-off-by: default avatarIcey <1790571317@qq.com>
parent 5089fd74
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/models/qwen3_next.py
View file @ 838d7116
......@@ -306,7 +306,7 @@ class Qwen3NextGatedDeltaNet(nn.Module, MambaBase):
eps=self.layer_norm_epsilon,
group_size=None,
norm_before_gate=True,
device=torch.cuda.current_device(),
device=current_platform.current_device(),
dtype=config.torch_dtype,
)
......
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