[Distributed][Core] Support Py39 and Py38 for PP (#6120)

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

vllm/executor/executor_base.py

@@ -123,12 +123,7 @@ class ExecutorAsyncBase(ExecutorBase):
         multimodal_config: Optional[MultiModalConfig],
         speculative_config: Optional[SpeculativeConfig],
     ) -> None:
-        # This locks each pipeline parallel stage so multiple virtual engines
+        self.pp_locks: Optional[List[asyncio.Lock]] = None
-        # can't execute on the same stage at the same time
-        self.pp_locks = [
-            asyncio.Lock()
-            for _ in range(parallel_config.pipeline_parallel_size)
-        ]
 
         super().__init__(model_config, cache_config, parallel_config,
                          scheduler_config, device_config, load_config,

vllm/executor/ray_gpu_executor.py

@@ -349,6 +349,15 @@ class RayGPUExecutorAsync(RayGPUExecutor, DistributedGPUExecutorAsync):
         self,
         execute_model_req: Optional[ExecuteModelRequest] = None
     ) -> List[SamplerOutput]:
+        if self.pp_locks is None:
+            # This locks each pipeline parallel stage so multiple virtual
+            # engines can't execute on the same stage at the same time
+            # We create the locks here to avoid creating them in the constructor
+            # which uses a different asyncio loop.
+            self.pp_locks = [
+                asyncio.Lock()
+                for _ in range(self.parallel_config.pipeline_parallel_size)
+            ]
 
         async def _run_task_with_lock(task, lock, *args, **kwargs):
             async with lock: