[BugFix] fix mix splitwise pickle load error (#5488)

* RouterArgs port str -> int

* fix race condition [is_fetching] causing multiple fetch requests

* bugfix: Delete duplicate input_ids tensor creation

* mm pd splitwise json -> pickle5; multimodal_inputs only pos id;
debuglog f to %s

* fix ENABLE_V1_KVCACHE_SCHEDULER=0 mm model lack pos_id, ...

* update cr

* Apply suggestions from code review

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* pre-commit fix

* rm multimodal_inputs deepcopy & fix rdma_cache_transfer.py tpsize=0

* fix mix splitwise pickle dump

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

fastdeploy/scheduler/splitwise_scheduler.py

@@ -525,7 +525,7 @@ class APIScheduler:
             req.disaggregate_info = None
             req_dict = req.to_dict()
             req_dict["group"] = group
-            req_str = orjson.dumps(req_dict)
+            req_str = pickle.dumps(req_dict, protocol=5)
             pkey = f"ReqQ_{pnode.nodeid}"
             # logger.info(f"Schedule Req {req_str} to Mixed")
             self.client.lpush(pkey, req_str)