[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/torchair/quantization/torchair_w8a8_dynamic.py

@@ -29,6 +29,7 @@ from vllm_ascend.torchair.ops.torchair_fused_moe import torchair_select_experts
 from vllm_ascend.torchair.utils import npu_stream_switch, npu_wait_tensor
 from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, AscendSocVersion,
                                dispose_tensor, get_ascend_soc_version,
+                               is_enable_nz,
                                is_hierarchical_communication_enabled)
 
 
@@ -829,7 +830,9 @@ class TorchairAscendW8A8DynamicLinearMethod:
         if self.transpose_weight:
             layer.weight.data = layer.weight.data.transpose(0, 1).contiguous()
         # cast quantized weight tensors in NZ format (29) for higher inference speed
-        layer.weight.data = torch_npu.npu_format_cast(layer.weight.data, 29)
+        if is_enable_nz():
+            layer.weight.data = torch_npu.npu_format_cast(
+                layer.weight.data, 29)
         layer.weight_scale.data = layer.weight_scale.data.flatten()
         layer.weight_scale_fp32 = layer.weight_scale.data.to(torch.float32)
         layer.weight_offset.data = layer.weight_offset.data.flatten()
@@ -1048,7 +1051,8 @@ class TorchairAscendW8A8DynamicFusedMoEMethod:
                 1, 2).contiguous()
             layer.w2_weight.data = layer.w2_weight.data.transpose(
                 1, 2).contiguous()
-        torch_npu.npu_format_cast_(layer.w2_weight, ACL_FORMAT_FRACTAL_NZ)
+        if is_enable_nz():
+            torch_npu.npu_format_cast_(layer.w2_weight, ACL_FORMAT_FRACTAL_NZ)
         layer.w13_weight_scale.data = layer.w13_weight_scale.data.view(
             layer.w13_weight_scale.data.shape[0], -1)
         layer.w13_weight_scale_fp32 = layer.w13_weight_scale.data.to(