[1/n] apply wna16marlin kernel in moe weight only quantization (#7683)

Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: yych0745 <1398089567@qq.com>
Co-authored-by: HandH1998 <1335248067@qq.com>
Co-authored-by: 弋云 <yiyun.wyt@antgroup.com>
Co-authored-by: walker-ai <2398833647@qq.com>

sgl-kernel/python/sgl_kernel/__init__.py

@@ -29,6 +29,7 @@ from sgl_kernel.elementwise import (
     rmsnorm,
     silu_and_mul,
 )
+from sgl_kernel.fused_moe import fused_marlin_moe
 from sgl_kernel.gemm import (
     awq_dequantize,
     bmm_fp8,
@@ -55,6 +56,11 @@ from sgl_kernel.kvcacheio import (
     transfer_kv_per_layer,
     transfer_kv_per_layer_mla,
 )
+from sgl_kernel.marlin import (
+    awq_marlin_moe_repack,
+    awq_marlin_repack,
+    gptq_marlin_repack,
+)
 from sgl_kernel.moe import (
     apply_shuffle_mul_sum,
     cutlass_fp4_group_mm,