add mlp tp optimze (#2120)

### What this PR does / why we need it?
For dense models, by not applying tensor parallelism (TP) to the
attention module and applying TP to the MLP module, the allreduce
operations in the attention module can be eliminated, thereby reducing
computational overhead. However, this approach increases memory usage,
so the environment variable VLLM_ASCEND_ENABLE_MLP_OPTIMZE is used to
control this optimization.

- vLLM main:
b17109beea

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>

tests/ut/test_utils.py

@@ -356,13 +356,13 @@ class TestUtils(TestBase):
         # ascend custom op is not registered
         utils.register_ascend_customop()
         # should call register_oot three
-        self.assertEqual(mock_customop.register_oot.call_count, 3)
+        self.assertEqual(mock_customop.register_oot.call_count, 6)
         self.assertTrue(utils._ASCEND_CUSTOMOP_IS_REIGISTERED)
 
         # ascend custom op is already registered
         utils.register_ascend_customop()
         # should not register_oot again, thus only called three in this ut
-        self.assertEqual(mock_customop.register_oot.call_count, 3)
+        self.assertEqual(mock_customop.register_oot.call_count, 6)
 
 
 class TestProfileExecuteDuration(TestBase):