[server_args] fix FA4 page_size auto-force for combined --attention-backend fa4 (#28825)

Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca> Co-authored-by: Brayden Zhong <brayden@radixark.ai>
2026-06-22 15:35:10 -07:00
parent a32f7111e4
commit 6c212a5d6b
2 changed files with 47 additions and 1 deletions
@@ -4651,7 +4651,11 @@ class ServerArgs:
            self.attention_backend = "triton"

        if (
-            self.prefill_attention_backend == "fa4"
+            (
+                self.attention_backend == "fa4"
+                or self.decode_attention_backend == "fa4"
+                or self.prefill_attention_backend == "fa4"
+            )
            and not self.use_mla_backend()
            and is_sm100_supported()
        ):