[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>

vllm_ascend/envs.py

@@ -97,6 +97,11 @@ env_variables: Dict[str, Callable[[], Any]] = {
     # between this feature and FLASHCOMM1, please refer to the feature guide in the documentation.
     "VLLM_ASCEND_FLASHCOMM2_PARALLEL_SIZE":
     lambda: int(os.getenv("VLLM_ASCEND_FLASHCOMM2_PARALLEL_SIZE", 0)),
+    # This feature is bound to the previous VLLM_ASCEND_FLASHCOMM2_PARALLEL_SIZE, and it adds the shared weight feature,
+    # which can eliminate redundant storage of weights. More detailed information can be found in PR#4188.
+    # We recommend that you enable it when Flashcomm2 is enabled and the VRAM capacity is limited.
+    "VLLM_ASCEND_ENABLE_FLASHCOMM2_OSHARED":
+    lambda: bool(int(os.getenv("VLLM_ASCEND_ENABLE_FLASHCOMM2_OSHARED", "0"))),
     # Whether to enable MLP weight prefetch, only used in small concurrency.
     "VLLM_ASCEND_ENABLE_PREFETCH_MLP":
     lambda: bool(int(os.getenv("VLLM_ASCEND_ENABLE_PREFETCH_MLP", '0'))),