[V1] port xformers backend to v1 (#21342)

Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
2025-08-05 10:04:46 -07:00
parent ae87ddd040
commit 469b3ffaaa
6 changed files with 438 additions and 1 deletions
--- a/vllm/v1/attention/backends/tree_attn.py
+++ b/vllm/v1/attention/backends/tree_attn.py
@@ -316,7 +316,6 @@ class TreeAttentionImpl(AttentionImpl):
        logits_soft_cap: Optional[float] = None,
        attn_type: AttentionType = AttentionType.DECODER,
        kv_sharing_target_layer_name: Optional[str] = None,
-        use_irope: bool = False,
    ) -> None:
        self.num_heads = num_heads
        self.head_size = head_size