[Feature]: implement the fusion of allreduce and matmul in prefill phase when tp is enabled (#1926)

### What this PR does / why we need it?
it'll execute allreduce and malmul seperately in vllm RowParallelLinear
forward funcion, this function use torch_npu.npu_mm_all_reduce_base to
execute allreduce and matmul in a fused kernel way. this will gain a 20%
performance
promotion in eager mode.
### Does this PR introduce _any_ user-facing change?
this PR introduce a new env `VLLM_ASCEND_ENABLE_MATMUL_ALLREDUCE` to
control whether enable the feature or not.

### How was this patch tested?
the patch is tested by adding a new test file `test_patch_linear.py` to
guard the ut


- vLLM version: v0.10.0
- vLLM main:
7728dd77bb

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>

vllm_ascend/envs.py

@@ -154,7 +154,11 @@ env_variables: Dict[str, Callable[[], Any]] = {
     # Whether to enable mla_pa for deepseek mla decode, this flag will be removed after its available torch_npu is public accessible
     # and the mla_pa will be the default path of deepseek decode path.
     "VLLM_ASCEND_MLA_PA":
-    lambda: int(os.getenv("VLLM_ASCEND_MLA_PA", 0))
+    lambda: int(os.getenv("VLLM_ASCEND_MLA_PA", 0)),
+    # Whether to enable MatmulAllReduce fusion kernel when tensor parallel is enabled.
+    # this feature is supported in A2, and eager mode will get better performance.
+    "VLLM_ASCEND_ENABLE_MATMUL_ALLREDUCE":
+    lambda: bool(int(os.getenv("VLLM_ASCEND_ENABLE_MATMUL_ALLREDUCE", '0'))),
 }
 
 # end-env-vars-definition