[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/xlite/xlite.py

@@ -26,10 +26,10 @@ from vllm.logger import logger
 from vllm.sequence import IntermediateTensors
 from xlite._C import AttnMHA, Model, ModelAttnMeta, ModelConfig, Runtime
 
+import vllm_ascend.envs as envs_ascend
 from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.attention.attention_v1 import (AscendAttentionState,
                                                 AscendMetadata)
-from vllm_ascend.utils import is_enable_nz
 
 
 class XliteModel:
@@ -134,7 +134,7 @@ class LlamaXliteModel(XliteModel):
         config.moe_tp_size = 1
 
         config.attn_type = AttnMHA
-        config.weight_nz = is_enable_nz()
+        config.weight_nz = envs_ascend.VLLM_ASCEND_ENABLE_NZ
         scheduler_config = vllm_config.scheduler_config
         max_batch_size = scheduler_config.max_num_seqs
         max_seq_len = vllm_config.model_config.max_model_len