[Feature] Support return logprob of generated tokens (#2784)

* online chat support logprobs

* check xpu

* check vl_gpu_model_runner

* only cuda support logprob

* get_worker() check platform

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

fastdeploy/engine/config.py

@@ -585,6 +585,7 @@ class Config:
         max_capture_batch_size: int = 64,
         guided_decoding_backend: Optional[str] = None,
         disable_any_whitespace: bool = False,
+        enable_logprob: bool = False,
     ):
         """
         Initialize the Config class.
@@ -678,6 +679,8 @@ class Config:
                                         self.parallel_config.expert_parallel_size), 8))])
         self.device_ids = os.getenv("CUDA_VISIBLE_DEVICES", self.device_ids)
 
+        self.enable_logprob = enable_logprob
+
         self.read_from_config()
         self.postprocess()
         self.check()