fix comment

Author: liuruyan

fastdeploy/engine/common_engine.py

@@ -2029,6 +2029,7 @@ def _start_worker_service(self):
             "use_internode_ll_two_stage": self.cfg.parallel_config.use_internode_ll_two_stage,
             "disable_sequence_parallel_moe": self.cfg.parallel_config.disable_sequence_parallel_moe,
             "enable_logprob": self.cfg.model_config.enable_logprob,
+            "compute_logits_stats": self.cfg.model_config.compute_logits_stats,
             "lm_head_fp32": self.cfg.model_config.lm_head_fp32,
             "enable_entropy": self.cfg.model_config.enable_entropy,
             "enable_overlap_schedule": self.cfg.scheduler_config.enable_overlap_schedule,

fastdeploy/entrypoints/openai/serving_chat.py

@@ -14,6 +14,8 @@
 # limitations under the License.
 """
 
+from __future__ import annotations
+
 import asyncio
 import itertools
 import time

fastdeploy/worker/output.py

@@ -59,10 +59,6 @@ def slice_columns(self, start: int, end: int):
             [row[start:end] for row in self.logprob_token_ids],
             [row[start:end] for row in self.logprobs],
             self.sampled_token_ranks,  # unchanged
-            # [row[start:end] for row in self.logits_min],
-            # [row[start:end] for row in self.logits_max],
-            # [row[start:end] for row in self.logits_mean],
-            # [row[start:end] for row in self.logits_std],
             self.logits_min,  # unchanged
             self.logits_max,  # unchanged
             self.logits_mean,  # unchanged