[Feat] Unquantized Linear to nz and control all nz-cast (#3356)

### What this PR does / why we need it?
Currently, when executing to the Linear layer of models in vLLM-Ascend,
the weights format is ND in unquantized case and skipped ascend case.
This PR supplements the execution logic for Linear layer. We use a new
global variable: VLLM_ASCEND_ENABLE_NZ. When VLLM_ASCEND_ENABLE_NZ=1 and
CANN version is 8.3, the weights of the Linear layer will be converted
to FRACTAL_NZ, in both unquantized case and skipped ascend case. We also
use VLLM_ASCEND_ENABLE_NZ to control the existing NZ conversion, such as
w8a8-quantized case.

### Does this PR introduce _any_ user-facing change?
Add a new global variable VLLM_ASCEND_ENABLE_NZ. If you want to use NZ
format, you should set VLLM_ASCEND_ENABLE_NZ=1.

### How was this patch tested?

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>

vllm_ascend/ops/common_fused_moe.py

@@ -37,7 +37,8 @@ from vllm_ascend.eplb.core.eplb_utils import (determine_default_expert_map,
 from vllm_ascend.ops.expert_load_balancer import ExpertLoadBalancer
 from vllm_ascend.ops.moe.experts_selector import select_experts
 from vllm_ascend.ops.moe.moe_comm_method import setup_moe_comm_method
-from vllm_ascend.utils import ACL_FORMAT_FRACTAL_NZ, is_310p, npu_stream_switch
+from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, is_310p, is_enable_nz,
+                               npu_stream_switch)
 
 
 class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
@@ -83,7 +84,7 @@ class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
             w2_data = self._maybe_pad_weight(layer.w2_weight.data)
             layer.w2_weight = torch.nn.Parameter(w2_data, requires_grad=False)
 
-        if not is_310p():
+        if not is_310p() and is_enable_nz():
             layer.w13_weight.data = torch_npu.npu_format_cast(
                 layer.w13_weight.data, ACL_FORMAT_FRACTAL_NZ)
             layer.w2_weight.data = torch_npu.npu_format_cast(