[Bugfix] rename enable_flash_comm_v1 back to enable_sp (#6883)

### What this PR does / why we need it?

PR #5632 introduced a bug by replacing some branches gated by enable_sp
with enable_flash_comm_v1. As a result, when enable_shared_expert_dp is
enabled alone (i.e., VLLM_ASCEND_ENABLE_FLASHCOMM1=0 and
VLLM_ASCEND_ENABLE_FLASHCOMM=0), the behavior becomes inconsistent with
the previous logic and leads to accuracy issues. This PR restores the
original enable_sp-based branching to recover expected behavior and
accuracy.

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?

#### 1. start server
``` bash
vllm serve /home/weights/DeepSeek-V2-Lite-W8A8/  \
    --port 8001 \
    --served-model-name auto \
    --max-model-len 1024 \
    --enforce-eager \
    --tensor-parallel-size 2 \
    --data-parallel-size 2 \
    --gpu-memory-utilization 0.9 \
    --enable-expert-parallel \
    --additional-config '{"enable_shared_expert_dp": true}'
```

#### 2. curl
```bash
curl -s http://localhost:8001/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
  "model": "auto",
  "messages": [
    {"role": "user", "content": "Hello. I have a question. Who are you?"}
  ],
  "max_tokens": 10,
  "temperature": 0.0,
  "ignore_eos_token": true
}'
```

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

vllm_ascend/utils.py

@@ -719,15 +719,6 @@ def matmul_allreduce_enable() -> bool:
     return envs_ascend.VLLM_ASCEND_ENABLE_MATMUL_ALLREDUCE
 
 
-def enable_flash_comm_v1():
-    return (
-        envs_ascend.VLLM_ASCEND_ENABLE_FLASHCOMM1
-        # Flash comm 1 should be enabled by env VLLM_ASCEND_ENABLE_FLASHCOMM1
-        # We retain the env VLLM_ASCEND_ENABLE_FLASHCOMM here for backward compatibility.
-        or bool(int(os.getenv("VLLM_ASCEND_ENABLE_FLASHCOMM", "0")))
-    )
-
-
 def enable_sp_by_pass(vllm_config: VllmConfig):
     return not vllm_config.model_config.enforce_eager and vllm_config.compilation_config.pass_config.enable_sp
 
@@ -739,7 +730,12 @@ def enable_sp(vllm_config=None, enable_shared_expert_dp: bool = False) -> bool:
             from vllm.config import get_current_vllm_config
 
             vllm_config = get_current_vllm_config()
-        _ENABLE_SP = enable_sp_by_pass(vllm_config) or enable_flash_comm_v1()
+        _ENABLE_SP = (
+            envs_ascend.VLLM_ASCEND_ENABLE_FLASHCOMM1
+            # Flash comm 1 should be enabled by env VLLM_ASCEND_ENABLE_FLASHCOMM1
+            # We retain the env VLLM_ASCEND_ENABLE_FLASHCOMM here for backward compatibility.
+            or bool(int(os.getenv("VLLM_ASCEND_ENABLE_FLASHCOMM", "0")))
+        )
 
         if not _ENABLE_SP and enable_shared_expert_dp:
             _ENABLE_SP = True
@@ -1104,7 +1100,7 @@ def enable_dsa_cp() -> bool:
     is_ds_v32 = hasattr(vllm_config.model_config, "hf_text_config") and hasattr(
         vllm_config.model_config.hf_text_config, "index_topk"
     )
-    return bool(is_ds_v32 and enable_flash_comm_v1())
+    return bool(is_ds_v32 and enable_sp())
 
 
 @lru_cache(maxsize=1)