diff --git a/vllm/model_executor/models/qwen3_next.py b/vllm/model_executor/models/qwen3_next.py index c97257053..abba104bf 100644 --- a/vllm/model_executor/models/qwen3_next.py +++ b/vllm/model_executor/models/qwen3_next.py @@ -501,6 +501,7 @@ class Qwen3NextGatedDeltaNet(nn.Module, MambaBase): self.A_log = nn.Parameter( torch.empty( divide(self.num_v_heads, self.tp_size), + dtype=torch.float32, ) )