[Quantization] Support compressed tensors w8a8 static and w8a8 dynamic weight (#4036)

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

While using the LLM Compressor quantization tool from the VLLM community
to generate quantized weights, the VLLM Ascend engine needs to be
adapted to support the compressed tensors quantization format.

1. Add AscendCompressedTensorsConfig to replace CompressedTensorsConfig
in vllm.
2. Support CompressedTensorsW8A8 static weight.
- weight: per-channel, int8, symmetric; activation: per-tensor, int8,
symmetric.
4. Support CompressedTensorsW8A8Dynamic weight.
- weight: per-channel, int8, symmetric; activation: per-token, int8,
symmetric, dynamic.
5. Modify the override_quantization_method in AscendQuantConfig.

Co-authored-by: taoqun110 taoqun@huawei.com
Co-authored-by: chenxi-hh chen464822955@163.com

- vLLM version: v0.11.2

---------

Signed-off-by: LHXuuu <scut_xlh@163.com>
Signed-off-by: chenxi-hh <chen464822955@163.com>
Signed-off-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>
Co-authored-by: chenxi-hh <chen464822955@163.com>
Co-authored-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>

tests/ut/quantization/test_quant_config.py

@@ -65,7 +65,7 @@ class TestAscendQuantConfig(TestBase):
         # Test when NPU is available
         mock_is_available.return_value = True
         result = AscendQuantConfig.override_quantization_method(None, None)
-        self.assertEqual(result, ASCEND_QUANTIZATION_METHOD)
+        self.assertIsNone(result)
 
         # Test when NPU is not available
         mock_is_available.return_value = False
@@ -93,7 +93,7 @@ class TestAscendQuantConfig(TestBase):
             self.assertIs(method, mock_ascend_linear.return_value)
             mock_ascend_linear.assert_called_once_with(
                 self.ascend_config, ".attn",
-                self.ascend_config.packed_modules_mapping)
+                self.ascend_config.packed_modules_mapping, linear_layer)
 
     def test_get_quant_method_for_attention(self):
         attention_layer = MagicMock(spec=Attention)