[AMD] Fix Qwen3-Coder-Next: Add missing k_scale/v_scale args to extend_attention_fwd in aiter_backend (#19736)

2026-03-03 22:01:08 -08:00
parent 5972f97f11
commit c6850ac30c
1 changed files with 2 additions and 0 deletions
--- a/python/sglang/srt/layers/attention/aiter_backend.py
+++ b/python/sglang/srt/layers/attention/aiter_backend.py
@@ -1765,6 +1765,8 @@ class AiterAttnBackend(AttentionBackend):
                    True,  # causal
                    self.forward_metadata.mask_indptr,
                    self.forward_metadata.max_extend_len,
+                    1.0,  # k_scale
+                    1.0,  # v_scale
                    layer.scaling,
                    logit_cap=layer.logit_cap,
                )