[RL][Cherry-Pick] Fix the out-of-bounds issue caused by int32 in the R3 kernel (#7155)

* [RL]Perf: Optimize batch delete prefix and fused put in R3 (#6604)

* Optimizate delete batch and fused put

* refine code

* refine code

* refine code

* Support suspend r3

* [RL] Fix R3 Empty bug with TP=1 (#6777)

* Fix int32 overflow

* refine code

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

fastdeploy/envs.py

@@ -253,6 +253,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
     "FD_SAVE_OUTPUT_CACHE_FOR_PREEMPTED_REQUEST": lambda: bool(
         int(os.getenv("FD_SAVE_OUTPUT_CACHE_FOR_PREEMPTED_REQUEST", "1"))
     ),
+    # Suspend rollouting routing replay
+    "FD_SUSPEND_ROUTING_REPLAY": lambda: bool(int(os.getenv("FD_SUSPEND_ROUTING_REPLAY", "0"))),
     # train-infer consistency, used in RL
     # Whether to align RoPE and moe gate precision with training
     "FD_ENABLE_RL": lambda: int(os.getenv("FD_ENABLE_RL", "0")),