[MM] Pass prefix parameter to MMEncoderAttention (#33674)

Signed-off-by: shen-shanshan <467638484@qq.com>
2026-02-03 22:47:41 +08:00
parent f3d8a34671
commit 5c4f2dd6ef
15 changed files with 58 additions and 11 deletions
--- a/vllm/model_executor/models/qwen3_omni_moe_thinker.py
+++ b/vllm/model_executor/models/qwen3_omni_moe_thinker.py
@@ -194,6 +194,7 @@ class Qwen3OmniMoeAudioAttention(nn.Module):
            num_heads=self.num_local_heads,
            head_size=self.head_dim,
            scale=self.scaling,
+            prefix=prefix,
        )

    def forward(