Fix a bug in BatchTokenIDOut & Misc style and dependency updates (#7457)

python/sglang/srt/managers/schedule_batch.py

@@ -788,6 +788,7 @@ class Req:
         self.multimodal_inputs = None
         self.grammar = None
         self.origin_input_ids = [0]  # set it to one token to skip the long prefill
+        self.return_logprob = False
         self.finished_reason = FINISH_ABORT(
             error_msg, HTTPStatus.BAD_REQUEST, "BadRequestError"
         )

python/sglang/srt/managers/scheduler.py

@@ -1374,7 +1374,14 @@ class Scheduler(
             )
             raise ValueError(msg)
 
-        if len(self.req_to_token_pool.free_slots) != self.req_to_token_pool.size:
+        if self.disaggregation_mode == DisaggregationMode.DECODE:
+            req_total_size = (
+                self.req_to_token_pool.size + self.req_to_token_pool.pre_alloc_size
+            )
+        else:
+            req_total_size = self.req_to_token_pool.size
+
+        if len(self.req_to_token_pool.free_slots) != req_total_size:
             msg = (
                 "req_to_token_pool memory leak detected!"
                 f"available_size={len(self.req_to_token_pool.free_slots)}, "

python/sglang/srt/managers/tokenizer_manager.py

@@ -1226,7 +1226,7 @@ class TokenizerManager:
                     state.last_output_offset = len(state.output_ids)
                 else:
                     state.output_ids.extend(recv_obj.output_ids[i])
-                    output_token_ids = state.output_ids
+                    output_token_ids = state.output_ids.copy()
 
                 out_dict = {
                     "output_ids": output_token_ids,