[FEAT] Refactor spec decode to support efficient padded speculation (#3528)

### What this PR does / why we need it?
1. Refactor the file `mtp_proposer.py`, splits torchair related codes
into `mtp_torchair_proposer.py`
2. According to https://github.com/vllm-project/vllm/pull/24539,
implements padded speculative decoding as described in
https://github.com/vllm-project/vllm/issues/21984.
### Does this PR introduce _any_ user-facing change?
User can use `disable_padded_drafter_batch` to disable/enable padded
speculation, default is `False`.
offline example:
```
speculative_config={"method": "deepseek_mtp", "num_speculative_tokens": 1, "disable_padded_drafter_batch": False}
```

### How was this patch tested?

- [x] egaer with pad/unpad:
- [x] aclgraph with pad/unpad
- [x] torchair with pad/unpad

performance test of deepseek-r1 with tp16、dp1
aclgraph with pad ITL: 168ms
aclgraph with unpad ITL: 169ms
original: 178ms


- vLLM version: v0.11.0rc3
- vLLM main:
83f478bb19

---------

Signed-off-by: xuyexiong <xuyexiong@huawei.com>

vllm_ascend/spec_decode/__init__.py

@@ -19,14 +19,21 @@
 from vllm_ascend.spec_decode.eagle_proposer import EagleProposer
 from vllm_ascend.spec_decode.mtp_proposer import MtpProposer
 from vllm_ascend.spec_decode.ngram_proposer import NgramProposer
+from vllm_ascend.torchair.torchair_mtp_proposer import TorchairMtpProposer
 
 
-def get_spec_decode_method(method, vllm_config, device, runner):
+def get_spec_decode_method(method,
+                           vllm_config,
+                           device,
+                           runner,
+                           is_torchair_graph=False):
     if method == "ngram":
         return NgramProposer(vllm_config, device, runner)
     elif method in ["eagle", "eagle3"]:
         return EagleProposer(vllm_config, device, runner)
     elif method == 'deepseek_mtp':
+        if is_torchair_graph:
+            return TorchairMtpProposer(vllm_config, device, runner)
         return MtpProposer(vllm_config, device, runner)
     else:
         raise ValueError("Unknown speculative decoding method: "