[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>

tests/ut/distributed/test_parallel_state.py

@@ -25,14 +25,10 @@ def mock_distributed():
          patch('torch.distributed.get_world_size', return_value=16), \
          patch('torch.distributed.get_backend', return_value='nccl'), \
          patch('vllm_ascend.distributed.parallel_state.get_world_group') as mock_group, \
-         patch('vllm_ascend.distributed.parallel_state.get_tp_group') as mock_tp_group, \
-         patch('vllm_ascend.distributed.parallel_state.get_dp_group') as mock_dp_group, \
-         patch('vllm_ascend.distributed.parallel_state.get_pp_group') as mock_pp_group:
+         patch('vllm_ascend.distributed.parallel_state.get_tp_group') as mock_tp_group:
         mock_group.return_value.local_rank = 0
         mock_group.return_value.device_group = MagicMock()
         mock_tp_group.return_value.world_size = 4
-        mock_dp_group.return_value.world_size = 2
-        mock_pp_group.return_value.world_size = 2
         yield
 
 
@@ -50,7 +46,6 @@ def test_init_ascend_model_parallel(mock_distributed, parallel_config):
     mock_vllm_config.kv_transfer_config.is_kv_producer = True
     mock_envs_ascend = MagicMock()
     mock_envs_ascend.VLLM_ASCEND_FLASHCOMM2_PARALLEL_SIZE = 2
-    mock_envs_ascend.VLLM_ASCEND_ENABLE_FLASHCOMM2_OSHARED = 0
     mock_envs_ascend.VLLM_ASCEND_ENABLE_CONTEXT_PARALLEL = 0
     with patch('vllm_ascend.distributed.parallel_state.model_parallel_initialized', return_value=False), \
          patch('vllm_ascend.distributed.parallel_state.init_model_parallel_group'), \