[bugfix](pcp) expand max_num_tokens for pcp pad (#5478)

### What this PR does / why we need it?
Since the [PR](https://github.com/vllm-project/vllm/pull/28988) for PCP
modifications to `GPUModelRunner` has not yet been merged into vLLM,
this PR temporarily requires adjustments to certain buffer sizes. These
changes can be reverted once the original
[PR](https://github.com/vllm-project/vllm/pull/28988) is merged.

### Does this PR introduce _any_ user-facing change?
No

- vLLM version: v0.13.0
- vLLM main:
5326c89803

Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>

vllm_ascend/worker/model_runner_v1.py

@@ -183,8 +183,15 @@ class ExecuteModelState(NamedTuple):
 class NPUModelRunner(GPUModelRunner):
 
     def __init__(self, vllm_config: VllmConfig, device: torch.device):
+        # TODO(qcs): These manual pad and unpad for GPUModelRunner are
+        # used to expand some buffers, which need to be reverted after
+        # the following PR is merged:
+        # https://github.com/vllm-project/vllm/pull/28988
+        max_pcp_pad_tokens = vllm_config.parallel_config.prefill_context_parallel_size * 2 * vllm_config.scheduler_config.max_num_seqs
+        vllm_config.scheduler_config.max_num_batched_tokens += max_pcp_pad_tokens
         with _torch_cuda_wrapper():
             super().__init__(vllm_config, device)
+        vllm_config.scheduler_config.max_num_batched_tokens -= max_pcp_pad_tokens
         self.max_num_tokens = self.scheduler_config.max_num_batched_tokens
         self.max_num_reqs = self.scheduler_config.max_num_seqs
         self.dp_size = vllm_config.parallel_config.data_parallel_size