[Feature] Refactor PCP &DCP related code (#5214)

### What this PR does / why we need it?
Refactor pcp& dcp related code. we use pcp_manager class to Unifiy
Manage pcp & dcp . as we do this , many code can be deleted from
model_runner, and can avoid break pcp & dcp by other developments.
RFC：https://github.com/vllm-project/vllm-ascend/issues/5449
### Does this PR introduce _any_ user-facing change?
NO

### How was this patch tested?

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: zzzzwwjj <34335947+zzzzwwjj@users.noreply.github.com>

tests/ut/spec_decode/test_mtp_proposer.py

@@ -225,21 +225,22 @@ class TestMtpProposer:
         mock_deps.runner.spec_decode_common_attn_metadata = MagicMock()
         mock_deps.runner.pcp_size = 2
         mock_deps.runner.dcp_size = 1
-        mock_deps.runner.input_ids_pcp_full = CpuGpuBuffer(
+        mock_deps.runner.pcp_manager = MagicMock()
+        mock_deps.runner.pcp_manager.input_ids_pcp_full = CpuGpuBuffer(
             32,
             dtype=torch.int32,
             pin_memory=False,
             device='cpu',
         )
-        mock_deps.runner.input_ids_pcp_full.cpu = \
+        mock_deps.runner.pcp_manager.input_ids_pcp_full.cpu = \
             torch.arange(32, dtype=torch.int32)
-        mock_deps.runner.query_start_loc_pcp_full = CpuGpuBuffer(
+        mock_deps.runner.pcp_manager.query_start_loc_pcp_full = CpuGpuBuffer(
             5,
             dtype=torch.int32,
             pin_memory=False,
             device='cpu',
         )
-        mock_deps.runner.query_start_loc_pcp_full.cpu = \
+        mock_deps.runner.pcp_manager.query_start_loc_pcp_full.cpu = \
             torch.tensor([0, 8, 16, 24, 32])
         mock_deps.positions = torch.arange(16, dtype=torch.int32)
         mock_deps.hidden_states = torch.zeros(16, 4096, dtype=torch.float16)