[main] add pd transfer for ascend scheduler (#2753)

### What this PR does / why we need it?
For offline scenarios, adjust the scheduling process to prioritize the
prefill phase of all requests, then process the decode phase of all
requests.

### How was this patch tested?

```
max_num_seqs=24,
additional_config={
    "ascend_scheduler_config":{
        "enabled": True,
        "enable_pd_transfer": True,
        "decode_max_num_seqs": 24,
        "enable_chunked_prefill": False
    }
},
```
| input | output | num prompts | max_num_seqs | dp | tp | scheduler |
tps |
| ------ | ------ | ---------- | ---------------- | ---- | ---- |
---------------- | --------------- |
| dapo-math-17K | 2K | 384 | 24 | 2 | 1 | v1 | 234.06 |
| dapo-math-17K | 2K | 384 | 24 | 2 | 1 | pd transfer | 239.59(+2.4%) |
| dapo-math-17K| 2K | 384 | 24 | 4 | 1 | v1 | 222.85 |
| dapo-math-17K| 2K | 384 | 24 | 4 | 1 | pd transfer | 225.81(+1.3%) |


- vLLM version: v0.10.1.1
- vLLM main:
6fb2788163

---------

Signed-off-by: CaranLic <740821011@qq.com>

vllm_ascend/core/schedule_config.py

@@ -28,6 +28,8 @@ class AscendSchedulerConfig(SchedulerConfig):
     num_scheduler_steps: int = 1
     scheduler_cls: Union[str, Type[object]] = (
         "vllm_ascend.core.scheduler.AscendScheduler")
+    enable_pd_transfer: bool = False
+    decode_max_num_seqs: int = 0
 
     @classmethod
     def initialize_from_config(
@@ -45,6 +47,8 @@ class AscendSchedulerConfig(SchedulerConfig):
         scheduler_config["num_scheduler_steps"] = 1
         scheduler_config["scheduler_cls"] = (
             "vllm_ascend.core.scheduler.AscendScheduler")
+        scheduler_config["enable_pd_transfer"] = False
+        scheduler_config["decode_max_num_seqs"] = 0
         # Override params in original SchedulerConfig with params in ascend_scheduler_config
         for k, _ in scheduler_config.items():
             if hasattr(ascend_scheduler_config, k):