[main][Bugfix] Remove the ZMQ communication setup on the D node (#4926)

In the PD separation scenario, the D node does not need to perform get
operations, and therefore does not need to create ZeroMQ (ZMQ)
communication.
- vLLM version: v0.12.0
- vLLM main:
vllm-project/vllm@ad32e3e

Signed-off-by: SlightwindSec <[email protected]>

Author: SlightwindSec

vllm_ascend/distributed/kvpool/ascend_store_connector.py

@@ -55,7 +55,7 @@ def __init__(self,
             )
 
             assert self.connector_worker is not None
-            if vllm_config.parallel_config.rank == 0:
+            if vllm_config.parallel_config.rank == 0 and self.kv_role != "kv_consumer":
                 self.lookup_server = LookupKeyServer(self.connector_worker,
                                                      vllm_config,
                                                      self.use_layerwise)

vllm_ascend/distributed/kvpool/pool_scheduler.py

@@ -20,13 +20,14 @@
 class KVPoolScheduler:
 
     def __init__(self, vllm_config: "VllmConfig", use_layerwise):
-        self.client = LookupKeyClient(vllm_config)
         self.use_layerwise = use_layerwise
         self.kv_role = vllm_config.kv_transfer_config.kv_role
         self.consumer_is_to_load = vllm_config.kv_transfer_config.kv_connector_extra_config.get(
             "consumer_is_to_load", False)
         self.load_async = vllm_config.kv_transfer_config.kv_connector_extra_config.get(
             "load_async", False)
+        self.client = LookupKeyClient(
+            vllm_config) if self.kv_role != "kv_consumer" else None
         # request_id -> (vllm cached tokes, kvpool cached tokens)
         self.load_specs: dict[str, LoadSpec] = {}
         self.pcp_size = getattr(vllm_config.parallel_config,
@@ -74,8 +75,8 @@ def get_num_new_matched_tokens(
         else:
             token_len = len(request.prompt_token_ids)
 
-        num_external_hit_tokens = self.client.lookup(token_len,
-                                                     request.block_hashes)
+        num_external_hit_tokens = self.client.lookup(  # type: ignore[union-attr]
+            token_len, request.block_hashes)
 
         if num_external_hit_tokens == request.num_tokens:
             num_external_hit_tokens -= 1