Fix num_tokens_pre_allocated in disaggregation log (sgl-project#7714)

Author: ZeldaHuang

python/sglang/srt/disaggregation/decode.py

@@ -416,6 +416,12 @@ def pop_preallocated(self) -> List[DecodeRequest]:
 
         return preallocated_reqs
 
+    @property
+    def num_tokens_pre_allocated(self):
+        return sum(
+            len(decode_req.req.fill_ids) for decode_req in self.transfer_queue.queue
+        )
+
     def _allocatable_tokens(
         self, retractable_tokens: Optional[int] = None, count_retracted: bool = True
     ) -> int:

python/sglang/srt/managers/scheduler.py

@@ -707,9 +707,6 @@ def init_disaggregation(self):
                 transfer_backend=self.transfer_backend,
             )
 
-            # Metric for pre-allocation
-            self.num_tokens_pre_allocated = 0
-
         elif self.disaggregation_mode == DisaggregationMode.PREFILL:
             # *2 for the headroom.
             buffer_size = self.max_running_requests * 2
@@ -1372,7 +1369,7 @@ def log_decode_stats(
             msg += f"accept len: {spec_accept_length:.2f}, "
 
         if self.disaggregation_mode == DisaggregationMode.DECODE:
-            msg += f"pre-allocated usage: {self.num_tokens_pre_allocated / self.max_total_num_tokens:.2f}, "
+            msg += f"pre-allocated usage: {self.disagg_decode_prealloc_queue.num_tokens_pre_allocated / self.max_total_num_tokens:.2f}, "
             msg += f"#retracted-req: {len(self.disagg_decode_prealloc_queue.retracted_queue)}, "
 
         msg += (