[ROCm][CI] Fix granite_speech test for gfx90a by selecting compatible attention backend (#37611)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

tests/models/multimodal/generation/test_granite_speech.py

@@ -39,7 +39,11 @@ models = [MODEL_NAME]
 def granite_speech_attention_config():
     """Return attention config for Granite Speech tests on ROCm."""
     if current_platform.is_rocm():
-        return {"backend": "ROCM_AITER_FA"}
+        from vllm.platforms.rocm import on_mi3xx
+
+        if on_mi3xx():
+            return {"backend": "ROCM_AITER_FA"}
+        return {"backend": "TRITON_ATTN"}
     return None