[feature]Pooling Features and PCP Adaptation (#4143)

This PR let pooling kv connector support pcp feature

- vLLM version: v0.11.2

---------

Signed-off-by: fjw <2270923832@qq.com>
Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
Co-authored-by: SlightwindSec <slightwindsec@gmail.com>

vllm_ascend/distributed/kvpool/pool_scheduler.py

@@ -29,7 +29,14 @@ class KVPoolScheduler:
             "load_async", False)
         # request_id -> (vllm cached tokes, kvpool cached tokens)
         self.load_specs: dict[str, LoadSpec] = {}
+        self.pcp_size = vllm_config.parallel_config.prefill_context_parallel_size
+        self.dcp_size = vllm_config.parallel_config.decode_context_parallel_size
+
         self._block_size = vllm_config.cache_config.block_size
+        if self.pcp_size > 1:
+            self._block_size *= self.pcp_size
+        if self.dcp_size > 1:
+            self._block_size *= self.dcp_size
         # request_id -> full_token_ids
         self._request_trackers: dict[str, RequestTracker] = {}
         # Whether to discard partial chunks