Use apply_rope_with_cos_sin_cache_inplace for DeepSeek (#4764)

Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
2025-03-27 01:45:37 -07:00
parent 8bf6d7f406
commit 886fcbdd09
1 changed files with 1 additions and 1 deletions
@@ -645,7 +645,7 @@ class DeepseekScalingRotaryEmbedding(RotaryEmbedding):
        cache = torch.cat((cos, sin), dim=-1)
        return cache

-    def forward(
+    def forward_native(
        self,
        positions: torch.Tensor,
        query: torch.Tensor,