[Feat] ernie4_5_vl_moe support CudaGraph (#3226)

* delete dynamic control flow for decode

* coda-style

* fix scatter/gather typos and use input stream instead default stream

* support 0-Size Tensor

* update runner and model

* using static mem address as input

* fix mem leak

* refine code

* update mm_buffer

* fix typo

* fix buffersize

* fix unk token

* refine code

* refine

* support other arch

* open cudagraph in vlci

* fix

* update

* update

* update

* fix cmd

* update

---------

Co-authored-by: aquagull <hongyuh@qq.com>
Co-authored-by: Yuanle Liu <yuanlehome@163.com>

custom_ops/gpu_ops/moe/moe_ffn.cu

@@ -412,7 +412,9 @@ const auto t_type = (quant_method == "w4a8") ? up_gate_proj_scale.get().dtype()
                     (quant_method == "w4afp8") ? paddle::DataType::BFLOAT16 :
                     permute_input.dtype();
     auto ffn_out = paddle::empty_like(permute_input, t_type);
-
+    if(permute_input.numel() == 0){
+        return ffn_out;
+    }
     switch (t_type) {
         case paddle::DataType::BFLOAT16:
             MoeFFNKernel<paddle::DataType::BFLOAT16>(permute_input,