[Feature] Support AWQ MoE W4A16 Quantization (#142)

Signed-off-by: tangshiwen <tangshiwen@baidu.com>
Co-authored-by: Li Wei <liwei.109@outlook.com>

vllm_kunlun/ops/__init__.py

@@ -19,6 +19,7 @@ import vllm_kunlun.ops.rotary_embedding
 import vllm_kunlun.ops.layernorm
 import vllm_kunlun.ops.quantization.awq
 import vllm_kunlun.ops.quantization.gptq
+import vllm_kunlun.ops.quantization.moe_wna16
 import vllm_kunlun.ops.vocab_parallel_embedding
 import vllm_kunlun.ops.linear
 import vllm_kunlun.ops.fused_moe.layer