[Feat] Flashcomm2 use o_shared linear (#4188)

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

It is mentioned in the [flashcomm2 technical
report](https://gitcode.com/ascend-tribe/ascend-inference-cluster/blob/main/FlashComm/FlashComm2%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86%E4%B8%AD%E4%BB%A5%E5%AD%98%E6%8D%A2%E4%BC%A0%E7%9A%84%E9%80%9A%E4%BF%A1%E4%BC%98%E5%8C%96%E6%8A%80%E6%9C%AF.pdf)
that FC2 will introduce full redundant storage of the o_proj matrix,
which will put pressure on the memory. Therefore, the technical report
proposed a compromise solution using otp2, but it will introduce
additional reduce-scatter communication.

We propose a shared linear feature (#2931 ) that supports distributing
weights layer by layer to each card, avoiding the need for TP splitting,
and can solve the memory issue.

This PR depends on #3232 and #2931

### Flashcomm2 flowchart
<img width="1142" height="878" alt="PixPin_2025-11-14_13-37-39"
src="https://github.com/user-attachments/assets/d45ea8db-d8ef-4d45-8e18-abd4d82ce3e0"
/>

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

Use environment variables
```bash
export VLLM_ASCEND_FLASHCOMM2_PARALLEL_SIZE=1
export VLLM_ASCEND_ENABLE_FLASHCOMM2_OSHARED=1
```


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

---------

Signed-off-by: zzhx1 <zzh_201018@outlook.com>
Signed-off-by: zzhxx <2783294813@qq.com>
Co-authored-by: zzh02232027 <zzh02232027@antgroup.com>
Co-authored-by: clrs97 <524936896@qq.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>

tests/ut/attention/test_mla_v1.py

@@ -6,6 +6,7 @@ from vllm.distributed.parallel_state import GroupCoordinator
 from vllm.model_executor.layers.linear import LinearBase
 
 from tests.ut.base import TestBase
+from vllm_ascend.ascend_config import init_ascend_config
 from vllm_ascend.attention.attention_v1 import AscendAttentionState
 from vllm_ascend.attention.mla_v1 import (AscendMLABackend,
                                           AscendMLADecodeMetadata,
@@ -845,6 +846,8 @@ class TestAscendMLAImpl(TestBase):
         model_config.dtype = torch.float16
         vllm_config.model_config = model_config
         get_current_vllm_config.return_value = vllm_config
+        vllm_config.additional_config = {"refresh": True}
+        init_ascend_config(vllm_config)
 
         num_heads = 256
         head_size = 1024

tests/ut/distributed/test_parallel_state.py

@@ -46,6 +46,7 @@ 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'), \