Add vae-patch-parallel-size and vae-use-tiling for HunyuanImage Benchmark (#5502)

Signed-off-by: zzh <943967662@qq.com>

tests/dfx/perf/tests/test_hunyuan_image3_it2i.json

@@ -94,6 +94,7 @@
                   "vae_patch_parallel_size": 2,
                   "enable_expert_parallel": true
                 },
+                "vae_use_tiling": true,
                 "input_connectors": {
                   "from_stage_0": "rdma_connector"
                 },

tests/dfx/perf/tests/test_hunyuan_image_tp2_cfgp2.json

@@ -21,6 +21,8 @@
         "deploy_config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
         "tensor-parallel-size": 2,
         "cfg-parallel-size": 2,
+        "vae-patch-parallel-size": 4,
+        "vae-use-tiling": true,
         "enable-diffusion-pipeline-profiler": true
       }
     },

tests/dfx/perf/tests/test_hunyuan_image_tp2_sp2.json

@@ -21,6 +21,8 @@
         "deploy-config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
         "tensor-parallel-size": 2,
         "ulysses-degree": 2,
+        "vae-patch-parallel-size": 4,
+        "vae-use-tiling": true,
         "enable-diffusion-pipeline-profiler": true
       }
     },

tests/dfx/perf/tests/test_hunyuan_image_tp4.json

@@ -20,6 +20,8 @@
       "serve_args": {
         "deploy-config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
         "tensor-parallel-size": 4,
+        "vae-patch-parallel-size": 4,
+        "vae-use-tiling": true,
         "enable-diffusion-pipeline-profiler": true
       }
     },