[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>

tests/ut/core/test_schedule_config.py

@@ -165,3 +165,16 @@ class TestAscendSchedulerConfig(TestBase):
         )
         self.assertIn("max_num_batched_tokens (2048)", str(context.exception))
         self.assertIn("max_model_len (4096)", str(context.exception))
+
+    def test_initialize_from_config_with_pd_transfer(self):
+        ascend_config = AscendSchedulerConfig.initialize_from_config(
+            self.basic_scheduler_config,
+            AscendSchedulerConfig(
+                enable_pd_transfer=True,
+                decode_max_num_seqs=48,
+                max_num_batched_tokens=4096,
+                max_model_len=4096,
+            ),
+        )
+        self.assertEqual(ascend_config.enable_pd_transfer, True)
+        self.assertEqual(ascend_config.decode_max_num_seqs, 48)