[BugFix][0.18.0] Fix quant_bias missing in w8a8_static when flashcomm1 is enabled for GLM-5 (#8304)

### What this PR does / why we need it?
PR #8220 in v0.18.0

In a previous PR #7843 , the o_proj layer of GLM-5 was reverted to TP
(Tensor Parallel) splitting when flashcomm1 was enabled. However, this
was a temporary workaround and did not address the root cause of the
precision issues observed in the o_proj layer under flashcomm1.

I am working on a definitive fix for this issue. Currently, a clear bug
has been identified in
880e20fdde/vllm_ascend/quantization/methods/w8a8_static.py (L124):
during quantized matrix multiplication, quant_bias is not added if
tp_rank > 0. In the flashcomm1 scenario, all ranks actually require the
addition of quant_bias, meaning tp_rank=0 should be passed to ensure the
bias is applied correctly.

This PR aims to resolve this logic error and fix the underlying
precision issue.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
glm5 e2e test

---------

Signed-off-by: zjks98 <zhangjiakang4@huawei.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: triomino <15924998+triomino@users.noreply.github.com>
Co-authored-by: zjks98 <zhangjiakang4@huawei.com>

vllm_ascend/quantization/method_adapters.py

@@ -29,7 +29,7 @@ from vllm.model_executor.utils import set_weight_attrs
 
 from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.distributed.parallel_state import get_flashcomm2_otp_group, get_mlp_tp_group, get_otp_group
-from vllm_ascend.utils import flashcomm2_enable, mlp_tp_enable, oproj_tp_enable
+from vllm_ascend.utils import enable_dsa_cp_with_layer_shard, flashcomm2_enable, mlp_tp_enable, oproj_tp_enable
 
 from .methods import AscendAttentionScheme, AscendLinearScheme, AscendMoEScheme, is_mx_quant_type
 
@@ -46,6 +46,7 @@ class AscendLinearMethod(LinearMethodBase):
 
     def __init__(self, scheme: AscendLinearScheme) -> None:
         self.quant_method = scheme
+        self._enable_dsa_cp_with_layer_shard = enable_dsa_cp_with_layer_shard()
 
     def create_weights(
         self,
@@ -145,6 +146,8 @@ class AscendLinearMethod(LinearMethodBase):
                     tp_rank = 0
                 else:
                     tp_rank = get_flashcomm2_otp_group().rank_in_group
+            elif layer.prefix.find("o_proj") != -1 and self._enable_dsa_cp_with_layer_shard:
+                tp_rank = 0
             else:
                 tp_rank = get_tensor_model_parallel_rank()
         else: