[Fusion] normalize fusion naming and enable e2e test (#4693)

### What this PR does / why we need it?
This PR standardizes the fusion naming, changing
`enable_quantization_fusion` to `fuse_norm_quant`, and enables e2e
testing.

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.

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

---------

Signed-off-by: wxsIcey <1790571317@qq.com>

vllm_ascend/compilation/graph_fusion_pass_manager.py

@@ -46,8 +46,8 @@ class GraphFusionPassManager:
         # By default, we enable the graph fusion and quantization fusion pass.
         self.ascend_compilation_config: dict = config.additional_config.get(
             "ascend_compilation_config", {})
-        if self.ascend_compilation_config.get("enable_quantization_fusion",
-                                              True):
-            from .passes.quant_fusion_pass import AddRMSNormQuantFusionPass
+        if self.ascend_compilation_config.get("fuse_norm_quant", True):
+            from .passes.norm_quant_fusion_pass import \
+                AddRMSNormQuantFusionPass
             self.passes.append(AddRMSNormQuantFusionPass(config))
         # Add more passes here as needed