[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>

vllm_ascend/_310p/quantization/modelslim_config.py

@@ -104,9 +104,9 @@ class AscendModelSlimConfig310(AscendModelSlimConfig):
         if isinstance(layer, LinearBase):
             packed = getattr(self, "packed_modules_mapping", {})
             if self.is_layer_skipped_ascend(prefix, packed):
-                from vllm_ascend.ops.linear import AscendUnquantizedLinearMethod
+                from vllm_ascend._310p.ops.linear import AscendUnquantizedLinearMethod310
 
-                return AscendUnquantizedLinearMethod()
+                return AscendUnquantizedLinearMethod310()
 
             scheme = create_scheme_for_layer(
                 quant_description=self.quant_description,