revert test

Signed-off-by: wangli <wangli858794774@gmail.com>

Author: Potabk

benchmarks/tests/latency-tests.json

@@ -1,4 +1,25 @@
 [
+  {
+    "test_name": "latency_qwen3_8B_tp1",
+    "parameters": {
+      "model": "Qwen/Qwen3-8B",
+      "tensor_parallel_size": 1,
+      "load_format": "dummy",
+      "max_model_len": 16384,
+      "num_iters_warmup": 5,
+      "num_iters": 15
+    }
+  },
+  {
+    "test_name": "latency_qwen2_5_7B_tp1",
+    "parameters": {
+      "model": "Qwen/Qwen2.5-7B-Instruct",
+      "tensor_parallel_size": 1,
+      "load_format": "dummy",
+      "num_iters_warmup": 5,
+      "num_iters": 15
+    }
+  },
   {
     "test_name": "latency_qwen3_30B_A3B_tp4",
     "parameters": {

benchmarks/tests/serving-tests.json

@@ -1,4 +1,79 @@
 [
+  {
+    "test_name": "serving_qwen2_5vl_7B_tp1",
+    "qps_list": [
+      1,
+      4,
+      16,
+      "inf"
+    ],
+    "server_parameters": {
+      "model": "Qwen/Qwen2.5-VL-7B-Instruct",
+      "tensor_parallel_size": 1,
+      "swap_space": 16,
+      "disable_log_stats": "",
+      "disable_log_requests": "",
+      "trust_remote_code": "",
+      "max_model_len": 16384
+    },
+    "client_parameters": {
+      "model": "Qwen/Qwen2.5-VL-7B-Instruct",
+      "endpoint_type": "openai-chat",
+      "dataset_name": "hf",
+      "hf_split": "train",
+      "endpoint": "/v1/chat/completions",
+      "dataset_path": "lmarena-ai/vision-arena-bench-v0.1",
+      "num_prompts": 200
+    }
+  },
+  {
+    "test_name": "serving_qwen3_8B_tp1",
+    "qps_list": [
+      1,
+      4,
+      16,
+      "inf"
+    ],
+    "server_parameters": {
+      "model": "Qwen/Qwen3-8B",
+      "tensor_parallel_size": 1,
+      "swap_space": 16,
+      "disable_log_stats": "",
+      "disable_log_requests": "",
+      "load_format": "dummy"
+    },
+    "client_parameters": {
+      "model": "Qwen/Qwen3-8B",
+      "endpoint_type": "vllm",
+      "dataset_name": "sharegpt",
+      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
+      "num_prompts": 200
+    }
+  },
+  {
+    "test_name": "serving_qwen2_5_7B_tp1",
+    "qps_list": [
+      1,
+      4,
+      16,
+      "inf"
+    ],
+    "server_parameters": {
+      "model": "Qwen/Qwen2.5-7B-Instruct",
+      "tensor_parallel_size": 1,
+      "swap_space": 16,
+      "disable_log_stats": "",
+      "disable_log_requests": "",
+      "load_format": "dummy"
+    },
+    "client_parameters": {
+      "model": "Qwen/Qwen2.5-7B-Instruct",
+      "endpoint_type": "vllm",
+      "dataset_name": "sharegpt",
+      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
+      "num_prompts": 200
+    }
+  },
   {
     "test_name": "serving_qwen3_30B_A3B_tp1",
     "qps_list": [

benchmarks/tests/throughput-tests.json

@@ -1,4 +1,39 @@
 [
+  {
+    "test_name": "throughput_qwen3_8B_tp1",
+    "parameters": {
+      "model": "Qwen/Qwen3-8B",
+      "tensor_parallel_size": 1,
+      "load_format": "dummy",
+      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
+      "num_prompts": 200,
+      "backend": "vllm"
+    }
+  },
+  {
+    "test_name": "throughput_qwen2_5vl_7B_tp1",
+    "parameters": {
+      "model": "Qwen/Qwen2.5-VL-7B-Instruct",
+      "tensor_parallel_size": 1,
+      "backend": "vllm-chat",
+      "dataset_name": "hf",
+      "hf_split": "train",
+      "max_model_len": 16384,
+      "dataset_path": "lmarena-ai/vision-arena-bench-v0.1",
+      "num_prompts": 200
+    }
+  },
+  {
+    "test_name": "throughput_qwen2_5_7B_tp1",
+    "parameters": {
+      "model": "Qwen/Qwen2.5-7B-Instruct",
+      "tensor_parallel_size": 1,
+      "load_format": "dummy",
+      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
+      "num_prompts": 200,
+      "backend": "vllm"
+    }
+  },
   {
     "test_name": "throughput_qwen3_30B_A3B_tp1",
     "parameters": {