[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (vllm-project#7766)

Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: LeiWang1999 <leiwang1999@outlook.com>

Author: 2 people

CMakeLists.txt

@@ -296,6 +296,11 @@ set(VLLM_MOE_EXT_SRC
   "csrc/moe/torch_bindings.cpp"
   "csrc/moe/topk_softmax_kernels.cu")
 
+if(VLLM_GPU_LANG STREQUAL "CUDA")
+  list(APPEND VLLM_MOE_EXT_SRC
+      "csrc/moe/marlin_moe_ops.cu")
+endif()
+
 define_gpu_extension_target(
   _moe_C
   DESTINATION vllm