[Feature] Support npuhraph_ex backend (#4700)

### What this PR does / why we need it?
We introduced the npugraph_ex backend through the vllm's adaptor
dispatch mechanism to accelerate aclgraph. This solution is based on
torch.compile and uses torchair to optimize the fx.graph. The
performance gains are mainly obtained from the static kernel. We
conducted tests on Qwen3-30B and achieved over 5% performance
optimization.

### Does this PR introduce _any_ user-facing change?
Yes, we add a new switch named"enable_npugraph_ex" in additional_config,
default is False.
We also add an example to show how to register custom replacement pass

### More information about this PR
This feature depends on the release of CANN and torch_npu in Q4. 
We tested it on a package that has not been publicly released yet and
verified that the functionality works.
This feature is still experimental at the moment; setting the config
true will directly raise error.
Merging into the main branch initially involves some preliminary commits
to facilitate subsequent development and testing of the feature, as well
as to avoid submitting an excessively large PR at once.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: chencangtao <chencangtao@huawei.com>
Signed-off-by: ChenCangtao <50493711+ChenCangtao@users.noreply.github.com>
Co-authored-by: chencangtao <chencangtao@huawei.com>
Co-authored-by: panchao-hub <315134829@qq.com>
Co-authored-by: wbigat <wbigat@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

vllm_ascend/platform.py

@@ -231,6 +231,7 @@ class NPUPlatform(Platform):
 
         if compilation_config.cudagraph_mode == CUDAGraphMode.NONE:
             compilation_config.mode = CompilationMode.NONE
+            ascend_config.enable_npugraph_ex = False
         elif compilation_config.cudagraph_mode == CUDAGraphMode.PIECEWISE:
             logger.info(
                 "PIECEWISE compilation enabled on NPU. use_inductor not supported - "
@@ -241,12 +242,14 @@ class NPUPlatform(Platform):
             compilation_config.use_inductor = False
             compilation_config.splitting_ops.extend(["vllm::mla_forward"])
             update_aclgraph_sizes(vllm_config)
+            ascend_config.enable_npugraph_ex = False
         elif compilation_config.cudagraph_mode == CUDAGraphMode.FULL_DECODE_ONLY or\
             compilation_config.cudagraph_mode == CUDAGraphMode.FULL:
             logger.info(
                 "FULL_DECODE_ONLY compilation enabled on NPU. use_inductor not supported - "
                 "using only ACL Graph mode")
             compilation_config.use_inductor = False
+            compilation_config.splitting_ops = []
             warning_message = """\033[91m
             **********************************************************************************
             * WARNING: You have enabled the *full graph* feature.
@@ -266,6 +269,7 @@ class NPUPlatform(Platform):
                 compilation_config.cudagraph_mode)
             compilation_config.cudagraph_mode = CUDAGraphMode.NONE
             compilation_config.mode = CompilationMode.NONE
+            ascend_config.enable_npugraph_ex = False
 
         # TODO: Remove this check when ACL Graph supports ASCEND_LAUNCH_BLOCKING=1
         # Then, we will have to discuss the error handling strategy and user experience