diff --git a/.buildkite/intel_jobs/model_executor_intel.yaml b/.buildkite/intel_jobs/model_executor_intel.yaml
index 5da075e235..d641c93e5a 100644
--- a/.buildkite/intel_jobs/model_executor_intel.yaml
+++ b/.buildkite/intel_jobs/model_executor_intel.yaml
@@ -28,16 +28,7 @@ steps:
       export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
       export PYTHONFAULTHANDLER=1 &&
       cd tests &&
-      pytest -v -s model_executor -m "not slow_test" --ignore="model_executor/layers/test_rocm_unquantized_gemm.py" --ignore="model_executor/model_loader/tensorizer_loader/test_tensorizer.py" --deselect="tests/model_executor/model_loader/test_reload.py::test_kv_scale_reload"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormModule::test_matches_reference_above_cudnn_grid_limit"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype0-out_dtype0]"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype1-out_dtype1]"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype2-out_dtype2]"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype3-out_dtype3]"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype4-out_dtype4]"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormDtypes::test_dtype_combinations[in_dtype5-out_dtype5]"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormShapes"
-      --deselect="tests/model_executor/layers/test_mm_input_norm.py::TestFusedMMInputNormInputHandling"'
+      pytest -v -s model_executor -m "not slow_test" --ignore="model_executor/layers/test_rocm_unquantized_gemm.py" --ignore="model_executor/model_loader/tensorizer_loader/test_tensorizer.py" --deselect="tests/model_executor/model_loader/test_reload.py::test_kv_scale_reload"'
 
 - label: Tensorizer Model Loader Tests (XPU)
   key: tensorizer-model-loader-tests-xpu
diff --git a/.buildkite/intel_jobs/models_multimodal_intel.yaml b/.buildkite/intel_jobs/models_multimodal_intel.yaml
index 061be1b136..89654ec3ae 100644
--- a/.buildkite/intel_jobs/models_multimodal_intel.yaml
+++ b/.buildkite/intel_jobs/models_multimodal_intel.yaml
@@ -73,7 +73,8 @@ steps:
       bash .buildkite/scripts/hardware_ci/run-intel-test.sh
       'cd tests &&
       pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma" &&
-      pytest -v -s models/multimodal/generation/test_gemma_ragged_audio.py -m core_model'
+      pytest -v -s models/multimodal/generation/test_gemma_ragged_audio.py -m core_model
+      pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model'
 
 - label: "Multi-Modal Models (Standard) 4: other + whisper"
   key: multi-modal-models-standard-4-other-whisper
diff --git a/vllm/model_executor/layers/fusion/mm_input_norm.py b/vllm/model_executor/layers/fusion/mm_input_norm.py
index 3dc6974c84..5de95b401d 100644
--- a/vllm/model_executor/layers/fusion/mm_input_norm.py
+++ b/vllm/model_executor/layers/fusion/mm_input_norm.py
@@ -313,19 +313,15 @@ class FusedMMInputNorm(CustomOp):
     def forward_xpu(
         self, pixel_values: torch.Tensor, visual_dtype: torch.dtype
     ) -> torch.Tensor:
-        """XPU fused custom kernel path.
-
-        On XPU, fuse the whole rescale + normalise into a single custom
-        kernel. The eager path materializes an fp32 intermediate and then
-        casts back, which adds device-side compute that cancels the
-        bandwidth saving of transferring uint8 pixel_values. The fused
-        kernel reads uint8 directly and writes ``visual_dtype`` in one pass.
+        """XPU fused custom kernel path for uint8 and Triton kernel path
+        for others.
         """
-        # The out-of-tree XPU kernel only supports the uint8 input that
-        # device-side normalisation guarantees; fail loudly otherwise.
-        assert pixel_values.dtype == torch.uint8, (
-            f"xpu_fused_input_norm requires uint8 input, got {pixel_values.dtype}"
-        )
+        if pixel_values.dtype != torch.uint8:
+            return self.forward_cuda(pixel_values, visual_dtype)
+
+        # For uint8 input, falls to xpu_fused_input_norm from xpu kernels
+        import vllm._xpu_ops  # noqa: F401
+
         return torch.ops.vllm.xpu_fused_input_norm(
             pixel_values, self.weight, self.bias, visual_dtype
         )