[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/quantization/utils.py

@@ -8,6 +8,7 @@ from vllm_ascend.utils import COMPRESSED_TENSORS_METHOD
 from .w4a4_flatquant_dynamic import AscendW4A4FlatQuantDynamicLinearMethod
 from .w4a8_dynamic import (AscendW4A8DynamicFusedMoEMethod,
                            AscendW4A8DynamicLinearMethod)
+from .w4a16 import AscendW4A16FusedMoEMethod
 from .w8a8 import (AscendC8KVCacheMethod, AscendW8A8FusedMoEMethod,
                    AscendW8A8LinearMethod)
 from .w8a8_dynamic import (AscendW8A8DynamicFusedMoEMethod,
@@ -16,6 +17,9 @@ from .w8a8_pdmix import (AscendW8A8PDMixFusedMoeMethod,
                          AscendW8A8PDMixLinearMethod)
 
 ASCEND_QUANTIZATION_METHOD_MAP: Dict[str, Dict[str, Type[Any]]] = {
+    "W4A16": {
+        "moe": AscendW4A16FusedMoEMethod,
+    },
     "W4A8_DYNAMIC": {
         "linear": AscendW4A8DynamicLinearMethod,
         "moe": AscendW4A8DynamicFusedMoEMethod,