Improve docs & Rename Gemini -> VertexAI (#19)

python/sglang/srt/managers/router/manager.py

@@ -28,7 +28,7 @@ class RouterManager:
         self.model_client = model_client
         self.recv_reqs = []
 
-        # Init Some Configs
+        # Init some configs
         self.extend_dependency_time = GLOBAL_BACKEND_CONFIG.extend_dependency_time
 
     async def loop_for_forward(self):
@@ -46,7 +46,7 @@ class RouterManager:
                 if has_finished:
                     await asyncio.sleep(self.extend_dependency_time)
 
-            await asyncio.sleep(0.001)
+            await asyncio.sleep(0.0006)
 
     async def loop_for_recv_requests(self):
         while True:

python/sglang/srt/managers/router/model_rpc.py

@@ -108,7 +108,7 @@ class ModelRpcServer(rpyc.Service):
         self.running_batch: Batch = None
         self.out_pyobjs = []
         self.decode_forward_ct = 0
-        self.stream_interval = 2
+        self.stream_interval = server_args.stream_interval
 
         # Init the FSM cache for constrained generation
         self.regex_fsm_cache = FSMCache(self.tokenizer)