enable npugraph_ex (#5120)

### What this PR does / why we need it?
We will expose the enabling switch for npugraph_ex to better facilitate
subsequent optimization.

### Does this PR introduce _any_ user-facing change?
Previously, the enable_npugraph_ex switch would trigger an error; now we
have removed the error reporting mechanism to better facilitate
subsequent optimization efforts.
Basic functionalities are available in CANN and torch_npu for Q3, while
advanced optimizations will depend on the Q4 release.

### How was this patch tested?
llm =LLM(
    model=model,
    enforce_eager=False ,
        additional_config={
        "enable_npugraph_ex":  True
        },
        compilation_config={
            "cudagraph_mode": "FULL_DECODE_ONLY",
            "cudagraph_capture_sizes": [16],
        },
}


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

---------

Signed-off-by: p00465316 <panchao13@huawei.com>
Co-authored-by: p00465316 <panchao13@huawei.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>

vllm_ascend/compilation/compiler_interface.py

@@ -89,13 +89,13 @@ def npugraph_ex_compile(
                                               tuple,
                                               args=([return_value], ))
         output_node.args = (tuple_node, )
-        fx_graph.recompile()
+        graph.recompile()
 
     import torchair
 
     # TODO: use a better way to lazy register replacement, instead of import one by one
     # As an example, we directly import here to register replacement.
-    import vllm_ascend.compilation.npugraph_ex_passes.add_rms_norm_quant  # noqa
+    # import vllm_ascend.compilation.npugraph_ex_passes.add_rms_norm_quant  # noqa
 
     torch.npu.set_compile_mode(jit_compile=False)
     config = torchair.CompilerConfig()