[Feat.][310P]: weightNZ feature with quant or unquant. (#6705)

NZ Format Support for Linear Layers: Implemented support for the NZ
(N-dimensional Z-order) format for linear layer weights on Ascend 310P,
enhancing performance for both quantized and unquantized layers.
Unquantized Linear Method for Ascend 310P: Introduced
AscendUnquantizedLinearMethod310 to specifically handle and apply NZ
format casting to unquantized linear layer weights during the loading
process.
MRotaryEmbedding Integration: Extended Rotary Embedding support by
adding AscendMRotaryEmbedding310 to provide an Ascend-specific
implementation for MRotaryEmbedding.
Quantization Method Updates: Updated the w8a8_static quantization method
to directly transpose weights and apply NZ format casting, ensuring
consistency with the new format.
- vLLM version: v0.15.0
- vLLM main:
9562912cea

---------

Signed-off-by: Tflowers-0129 <2906339855@qq.com>

tests/ut/_310p/quantization/test_modelslim_config_310.py

@@ -21,8 +21,8 @@ from vllm.model_executor.layers.linear import LinearBase
 
 from tests.ut.base import TestBase
 from vllm_ascend._310p.fused_moe.fused_moe import AscendUnquantizedFusedMoEMethod310
+from vllm_ascend._310p.ops.linear import AscendUnquantizedLinearMethod310
 from vllm_ascend._310p.quantization.modelslim_config import AscendModelSlimConfig310
-from vllm_ascend.ops.linear import AscendUnquantizedLinearMethod
 
 
 class TestAscendModelSlimConfig310(TestBase):
@@ -50,7 +50,7 @@ class TestAscendModelSlimConfig310(TestBase):
             patch.object(self.ascend_config, "is_layer_skipped_ascend", return_value=True),
         ):
             method = self.ascend_config.get_quant_method(linear_layer, ".attn")
-            self.assertIsInstance(method, AscendUnquantizedLinearMethod)
+            self.assertIsInstance(method, AscendUnquantizedLinearMethod310)
 
         # Test quantized layer
         mock_scheme = MagicMock()