[3/N][refactor] refactoer quantization (#2504)

### What this PR does / why we need it?
Move torchair related qunatization section into torchair dir to make the
code clear. Next step we'll remove all torchair related code outside of
torchair quantization.

### Does this PR introduce _any_ user-facing change?
NO

### How was this patch tested?
vLLM version: main
vLLM main:
ab9f2cfd19


- vLLM version: v0.10.1.1
- vLLM main:
959783fb99

Signed-off-by: hust17yixuan <303660421@qq.com>

tests/ut/torchair/test_utils.py

@@ -6,6 +6,7 @@ from unittest.mock import MagicMock, patch
 import torch
 
 from tests.ut.base import TestBase
+from vllm_ascend.quantization.quantizer import SUPPORT_ASCEND_QUANTIZER_TYPE
 from vllm_ascend.torchair import utils
 
 
@@ -120,3 +121,15 @@ class TestTorchairUtils(TestBase):
 
         utils.converting_weight_acl_format(model, ACL_FORMAT_FRACTAL_NZ)
         mock_npu_cast.assert_not_called()
+
+    def test_torchair_quant_method_register(self):
+
+        TorchairW8A8DYNAMICQuantizer = SUPPORT_ASCEND_QUANTIZER_TYPE[
+            "W8A8_DYNAMIC"]
+        TorchairW4A8DYNAMICQuantizer = SUPPORT_ASCEND_QUANTIZER_TYPE[
+            "W4A8_DYNAMIC"]
+        utils.torchair_quant_method_register()
+        self.assertNotEqual(TorchairW8A8DYNAMICQuantizer,
+                            SUPPORT_ASCEND_QUANTIZER_TYPE["W8A8_DYNAMIC"])
+        self.assertNotEqual(TorchairW4A8DYNAMICQuantizer,
+                            SUPPORT_ASCEND_QUANTIZER_TYPE["W4A8_DYNAMIC"])