[Feat] Support native Kimi-K2-Thinking native W4A16 quantized experts weights (#4516)

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

Adds W4A16 quantization method for the Kimi-K2-Thinking model and
updates relevant modules to support the new quantization method.

- Implements complete W4A16 quantization method including weight
packing/unpacking, per-group quantization parameter generation,
post-processing logic and MoE method application.
- Adds parameters `use_int4_w4a16`, `w1_offset` and `w2_offset`, adjusts
`with_quant` conditional logic to support W4A16 matrix multiplication.
- Adds `packed_modules_model_mapping` for Kimi-K2-Thinking model and
processing logic for `weight_packed` field.

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

---------

Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>
Signed-off-by: Ruri <33858552+zhoux77899@users.noreply.github.com>
Signed-off-by: Ruri <zhouxiang100@huawei.com>

vllm_ascend/ops/rotary_embedding.py

@@ -65,8 +65,8 @@ def _rope_forward_oot(
         raise NotImplementedError(
             "Batched rotary embedding is currently not supported on NPU.")
     else:
-        if self.cos is not None and \
-            self.sin is not None:
+        if hasattr(self, "cos") and hasattr(self, "sin") and \
+            self.cos is not None and self.sin is not None:
             # If cos and sin are generated outside, use npu_apply_rotary_pos_emb to avoid redundant calculation.
             # This method requires head_size and rotary_dim equal 128 and neox_style is True
             query = query.contiguous().view(1, query.shape[0], -1,