[Kernel] Zero point support in fused MarlinMoE kernel + AWQ Fused MoE (vllm-project#8973)

Co-authored-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <ds3822@columbia.edu>
Signed-off-by: Amit Garg <mitgarg17495@gmail.com>

Author: 2 people

CMakeLists.txt

@@ -433,6 +433,8 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
         "csrc/moe/marlin_kernels/marlin_moe_kernel_ku4b8.cu"
         "csrc/moe/marlin_kernels/marlin_moe_kernel_ku8b128.h"
         "csrc/moe/marlin_kernels/marlin_moe_kernel_ku8b128.cu"
+        "csrc/moe/marlin_kernels/marlin_moe_kernel_ku4.h"
+        "csrc/moe/marlin_kernels/marlin_moe_kernel_ku4.cu"
         "csrc/moe/marlin_moe_ops.cu")
 
     set_gencode_flags_for_srcs(