[refactor] refactor weight trans nz and transpose (#4878)

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

Now `VLLM_ASCEND_ENABLE_NZ` will have three options:
0: disable nz;
1: only quant case enable nz;
2: enable nz as long as possible;

And `VLLM_ASCEND_ENABLE_NZ`=1 by default.

All cases are shown in the table below:

|  | W4A4 | W4A8 | W8A8 | fp16/bf16 | fp32 |
|---|---|---|---|---|---|
| trans nz | can't support nz | trans nz by default | trans nz by
default | trans nz when VLLM_ASCEND_ENABLE_NZ is 2 | can't support nz |
| transpose | only support not transpose case | only support transpose
case | only support transpose case | linear: only support not transpose
case<br>gmm: only support transpose case | same to fp16/bf16 |

Some exceptional cases:
1. MLAPO op need to do some additional processing on the weights,
including trans nz. If use MLAPO op, some weight will be transformed to
nz forcely;
2. MLA/SFA's weight `W_UV` will be used by op
`torch.ops._C_ascend.batch_matmul_transpose`, and this op can't support
nz currently;

### Does this PR introduce _any_ user-facing change?
Now fp16/bf16 weight will not trans nz by default.

### How was this patch tested?

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

Signed-off-by: zzzzwwjj <1183291235@qq.com>

vllm_ascend/quantization/w4a4_flatquant_dynamic.py

@@ -86,7 +86,6 @@ class AscendW4A4FlatQuantDynamicLinearMethod:
     input_size = 0
 
     def __init__(self):
-        self.transpose_weight = False
         self.sym = True
 
     @staticmethod
@@ -176,9 +175,8 @@ class AscendW4A4FlatQuantDynamicLinearMethod:
         return output
 
     def process_weights_after_loading(self, layer):
+        # NOTE: Currently, w4a4 can't support weight nz
         weight_packed = pack_int4_weights(layer.weight.data)
-        if self.transpose_weight:
-            weight_packed = weight_packed.transpose(0, 1).contiguous()
         layer.register_parameter(
             'weight_packed',
             torch.nn.Parameter(weight_packed, requires_grad=False))