[rollout] fix: remove unexpected concurrency bound at 1000

Author: tongyuantongyu

verl/workers/rollout/replica.py

@@ -91,7 +91,7 @@ def __init__(
         is_reward_model: bool = False,
     ) -> None:
         self.replica_rank = replica_rank
-        self.config = omega_conf_to_dataclass(config)
+        self.config: RolloutConfig = omega_conf_to_dataclass(config)
         self.model_config: HFModelConfig = model_config
 
         self.world_size = (
@@ -220,6 +220,12 @@ def server_handle(self) -> ActorHandle:
         """Get rollout server handle for Token-in-token-out generation."""
         return self._server_handle
 
+    @property
+    def max_concurrency(self) -> int:
+        # 1000 is Ray's default max_concurrency for async execution.
+        # Add some margin to account for control call.
+        return max(1000, self.config.max_num_seqs + 4)
+
     def rollout_worker_use_gpu(self) -> bool:
         return True
 

verl/workers/rollout/sglang_rollout/async_sglang_server.py

@@ -505,6 +505,7 @@ async def launch_servers(self):
                 ),
                 runtime_env={"env_vars": {f"RAY_EXPERIMENTAL_NOSET_{visible_devices_keyword}": "1"}},
                 name=name,
+                max_concurrency=self.max_concurrency,
             ).remote(
                 config=self.config,
                 model_config=self.model_config,

verl/workers/rollout/trtllm_rollout/trtllm_async_server.py

@@ -353,6 +353,7 @@ async def launch_servers(self):
             ),
             runtime_env={"env_vars": {"RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES": "1"}},
             name=name,
+            max_concurrency=self.max_concurrency,
         ).remote(
             config=self.config,
             model_config=self.model_config,

verl/workers/rollout/vllm_rollout/vllm_async_server.py

@@ -840,6 +840,7 @@ async def launch_servers(self):
                 ),
                 runtime_env={"env_vars": {"RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES": "1"}},
                 name=name,
+                max_concurrency=self.max_concurrency,
             ).remote(
                 config=self.config,
                 model_config=self.model_config,