Add DeepSeek V3.2 support (#3270)

### What this PR does / why we need it?

This PR added the initial DeepSeek V3.2 support with [vLLM
v0.11.0](https://github.com/vllm-project/vllm/tree/releases/v0.11.0)
(not released yet). We will complete vLLM adaptation as soon as
possible. This feature will be ready in recent 1-2 days.

Related doc: https://github.com/vllm-project/vllm-ascend/pull/3223 .

### Does this PR introduce _any_ user-facing change?
Yes!

### How was this patch tested?
CI passed and Run deepseek doc soon.


- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: zzzzwwjj <1183291235@qq.com>
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Signed-off-by: wxsIcey <1790571317@qq.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: zzzzwwjj <1183291235@qq.com>
Co-authored-by: linfeng-yuan <1102311262@qq.com>
Co-authored-by: wxsIcey <1790571317@qq.com>
Co-authored-by: MengqingCao <cmq0113@163.com>

vllm_ascend/spec_decode/mtp_proposer.py

@@ -603,10 +603,11 @@ class MtpProposer(Proposer):
         torch.npu.set_compile_mode(jit_compile=False)
         if not self.runner.use_cached_npu_graph:
             npu_backend = torchair.get_npu_backend(compiler_config=config)
-            self.torchair_compiled_model = torch.compile(self.model,
-                                                         dynamic=True,
-                                                         fullgraph=True,
-                                                         backend=npu_backend)
+            self.torchair_compiled_model = torch.compile(
+                self.model,
+                dynamic=not get_ascend_config().use_sfa,
+                fullgraph=True,
+                backend=npu_backend)
             return self.torchair_compiled_model
         else:
             # Generate a new forward proxy code object to prevent the invalidation of
@@ -627,7 +628,7 @@ class MtpProposer(Proposer):
             self.torchair_compiled_models[
                 batch_size] = torchair.inference.cache_compile(
                     self.model.__dict__[forward_proxy_name],
-                    dynamic=True,
+                    dynamic=not get_ascend_config().use_sfa,
                     fullgraph=True,
                     cache_dir=TORCHAIR_CACHE_DIR,
                     config=config,