KVCache Transfer via Layer-wise Strategy in Disaggregation (#2602)

### What this PR does / why we need it?
See RFC: https://github.com/vllm-project/vllm-ascend/issues/2470 This PR
add a new kv connector for layer-wised kv transfer

### Does this PR introduce _any_ user-facing change?
yes, a new kv connector is added. User can use layer wised feature now.
### How was this patch tested?


- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

---------

Signed-off-by: leichao.lc <leichao139636@163.com>
Signed-off-by: CaveNightingale <2859066733@qq.com>
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Signed-off-by: hanxinlong <50882499@qq.com>
Signed-off-by: liziyu <liziyu16@huawei.com>
Co-authored-by: CaveNightingale <2859066733@qq.com>
Co-authored-by: nwpu-zxr <zhouxuerong2@huawei.com>
Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com>
Co-authored-by: hanxinlong <50882499@qq.com>

vllm_ascend/ascend_config.py

@@ -94,6 +94,17 @@ class AscendConfig:
                 raise AssertionError(
                     "oproj_tensor_parallel_size is only supported in pd scenario and can only be used in D node."
                 )
+        self.pd_tp_ratio = 1
+        if vllm_config.kv_transfer_config is not None and not vllm_config.model_config.is_deepseek_mla:
+            prefill_tp_size = vllm_config.kv_transfer_config.get_from_extra_config(
+                "prefill", {"tp_size": 1})["tp_size"]
+            decode_tp_size = vllm_config.kv_transfer_config.get_from_extra_config(
+                "decode", {"tp_size": 1})["tp_size"]
+            pd_tp_ratio: int = prefill_tp_size // decode_tp_size
+            self.pd_tp_ratio = pd_tp_ratio
+            if self.pd_tp_ratio == 0:
+                raise AssertionError(
+                    "Only support P node tp size lagger then D node tp size")
 
 
 class TorchairGraphConfig: