[v0.18.0][BugFix] Fix bug of precision when DSA-CP is enabled on GLM5 (#7843)

### What this PR does / why we need it?
This PR fixs accuracy bug in some cases with additional communication
methods.
This PR is a specific fix for version 0.18.0

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

### How was this patch tested?
CI passed with new added/existing test.
- vLLM version: v0.18.0
- vLLM main:
35141a7eed

---------

Signed-off-by: rjg-lyh <1318825571@qq.com>
Signed-off-by: yydyzr <liuyuncong1@huawei.com>
Co-authored-by: rjg-lyh <1318825571@qq.com>

vllm_ascend/ops/linear_op.py

@@ -663,7 +663,11 @@ def _get_row_parallel_op(
     | None
 ):
     if enable_dsa_cp_with_layer_shard() and "o_proj" in prefix:
-        return ShardedCPRowParallelOp(layer)
+        from vllm.config import get_current_vllm_config
+
+        vllm_config = get_current_vllm_config()
+        if vllm_config.model_config.hf_config.model_type not in ["glm_moe_dsa"]:
+            return ShardedCPRowParallelOp(layer)
     if "down_proj" in prefix and mlp_tp_enable() and not is_moe_layer(prefix):
         return MLPRowParallelOp(layer)
     if "o_proj" in prefix and oproj_tp_enable():