[ROCM][CI] Fix AMD Examples Test Group (#30276)

Signed-off-by: Yida Wu <yida.wu@amd.com>
Signed-off-by: Yida <yida.wu@amd.com>

examples/offline_inference/basic/embed.py

@@ -4,6 +4,9 @@
 from argparse import Namespace
 
 from vllm import LLM, EngineArgs
+from vllm.attention.backends.registry import AttentionBackendEnum
+from vllm.config import AttentionConfig
+from vllm.platforms import current_platform
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 
 
@@ -20,6 +23,11 @@ def parse_args():
 
 
 def main(args: Namespace):
+    if current_platform.is_rocm():
+        args.attention_config = AttentionConfig(
+            backend=AttentionBackendEnum.FLEX_ATTENTION
+        )
+
     # Sample prompts.
     prompts = [
         "Hello, my name is",