Use triton qk_norm both in Prefill and Decode (#7213)

Co-authored-by: “liuruian” <liuruian@baidu.com>

fastdeploy/model_executor/layers/normalization.py

@@ -341,7 +341,7 @@ class QKRMSNorm(nn.Layer):
         forward_meta,
         proxy_rmsnorm=None,
     ) -> paddle.Tensor:
-        if proxy_rmsnorm is None and self.qk_norm_fused and forward_meta.step_use_cudagraph:
+        if proxy_rmsnorm is None and self.qk_norm_fused:
             qkv_out = qk_rmsnorm_fused(
                 qkv_out,
                 self.q_norm.weight,

tests/e2e/test_Qwen3VL_serving.py

@@ -173,7 +173,7 @@ def test_consistency_between_runs(api_url, headers, consistent_payload):
     content1 = result1["choices"][0]["message"]["content"]
 
     # base result
-    content2 = "视频中手机支架的颜色是黑色的。"
+    content2 = "视频中手机支架的颜色是黑色。"
 
     # Verify that result is same as the base result
     assert content1.startswith(content2), content1