[Frontend] Add LLM.reward specific to reward models (#21720)

Signed-off-by: wang.yuqi <noooop@126.com>

examples/offline_inference/basic/embed.py

@@ -12,10 +12,9 @@ def parse_args():
     parser = EngineArgs.add_cli_args(parser)
     # Set example specific arguments
     parser.set_defaults(
-        model="intfloat/e5-mistral-7b-instruct",
+        model="intfloat/e5-small",
         runner="pooling",
         enforce_eager=True,
-        max_model_len=1024,
     )
     return parser.parse_args()