[refactor] Refactor the interface for shard weight and remove the flashcomm2 o_shared interface. (#5181)

### What this PR does / why we need it?
- Delete the environment variable
`VLLM_ASCEND_ENABLE_FLASHCOMM2_OSHARED`
- Introduce layer_sharding as a configurable feature in
additional_config
- Revise the term "shared weight" to "shard weight."
Configuration : The feature is opt-in via the additional_config
argument:
```
--additional-config '{
  "layer_sharding": ["o_proj", "q_b_proj"]
}'
```

This is orthogonal to standard tensor parallelism and weight replication
strategies. It is treated as a separate, explicit feature.It can be used
in any scenario, combined with the
flashcomm2https://github.com/vllm-project/vllm-ascend/pull/3232 feature
or the ShardedCP #4702 feature, to achieve significant performance.



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

---------

Signed-off-by: zzhx1 <zzh_201018@outlook.com>
Signed-off-by: zzhxx <zhangzihang23@mails.ucas.ac.cn>
Signed-off-by: chenxiao <Jaychou1620@Gmail.com>
Co-authored-by: clrs97 <524936896@qq.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>
Co-authored-by: chenxiao <Jaychou1620@Gmail.com>

vllm_ascend/ascend_config.py

@@ -51,6 +51,12 @@ class AscendConfig:
             "weight_prefetch_config", {})
         self.weight_prefetch_config = WeightPrefetchConfig(
             weight_prefetch_config)
+        self.layer_sharding = additional_config.get("layer_sharding", None)
+        logger.info_once(
+            f"Linear layer sharding enabled with config: {self.layer_sharding}. "
+            "Note: This feature works optimally with FLASHCOMM2 and DSA-CP enabled; "
+            "using it without these features may result in significant performance degradation."
+        )
 
         # Todo: Once https://github.com/vllm-project/vllm/issues/22246 is merged in vllm. Remove this config
         self.expert_map_path = additional_config.get("expert_map_path", None)
@@ -111,7 +117,7 @@ class AscendConfig:
         self.SLO_limits_for_dynamic_batch = additional_config.get(
             "SLO_limits_for_dynamic_batch", -1)
         from vllm_ascend.utils import get_flashcomm2_config_and_validate
-        self.flashcomm2_oproj_tensor_parallel_size, self.flashcomm2_oproj_shared = get_flashcomm2_config_and_validate(
+        self.flashcomm2_oproj_tensor_parallel_size = get_flashcomm2_config_and_validate(
             self, vllm_config)
         self.enable_npugraph_ex = additional_config.get(
             "enable_npugraph_ex", False)