[Bugfix] Fix missing scale passing for encoder Triton Attention implementation (#32149)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

examples/offline_inference/basic/embed.py

@@ -4,10 +4,7 @@
 from argparse import Namespace
 
 from vllm import LLM, EngineArgs
-from vllm.config import AttentionConfig
-from vllm.platforms import current_platform
 from vllm.utils.argparse_utils import FlexibleArgumentParser
-from vllm.v1.attention.backends.registry import AttentionBackendEnum
 
 
 def parse_args():
@@ -23,11 +20,6 @@ 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",