[CI][Benchmark] Add new model and v1 test to perf benchmarks (#1099)

### What this PR does / why we need it?
- Add qwen2.5-7b-instruct test
- Add v1 test
---------

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

.github/workflows/nightly_benchmarks.yaml

@@ -45,13 +45,18 @@ jobs:
   test:
     if: ${{ contains(github.event.pull_request.labels.*.name, 'performance-test') && contains(github.event.pull_request.labels.*.name, 'ready-for-test') || github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
 
-    name: Benchmarks/vLLM=${{ matrix.vllm_branch }}, vLLM-Ascend=${{ matrix.vllm_ascend_branch }}
+    name: Benchmarks/vLLM=${{ matrix.vllm_branch }}, vLLM-Ascend=${{ matrix.vllm_ascend_branch }}, use_v1=${{ matrix.vllm_use_v1 }}
     runs-on: 'linux-arm64-npu-static-8'
     strategy:
       matrix:
         include:
           - vllm_branch: v0.9.1
             vllm_ascend_branch: main
+            vllm_use_v1: 0
+          - vllm_branch: v0.9.0
+            vllm_ascend_branch: main
+            vllm_use_v1: 1
+      max-parallel: 1
     container:
       image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10
       volumes:
@@ -71,6 +76,7 @@ jobs:
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
         ES_OM_DOMAIN: ${{ secrets.ES_OM_DOMAIN }}
         ES_OM_AUTHORIZATION: ${{ secrets.ES_OM_AUTHORIZATION }}
+        VLLM_USE_V1: ${{ matrix.vllm_use_v1 }}
     steps:
       - name: Check npu and CANN info
         run: |
@@ -140,7 +146,7 @@ jobs:
       - name: Install elastic_tool
         if: github.event_name != 'pull_request'
         run: |
-          pip install escli-tool==0.2.1
+          pip install escli-tool==0.2.2
           
       - name: Collect pr info from vllm-project/vllm-ascend
         if: github.event_name != 'pull_request'
@@ -177,17 +183,17 @@ jobs:
             echo "vllm branch: ${{ matrix.vllm_branch }}"
             echo "vllm-ascend branch: ${{ matrix.vllm_ascend_branch }}"
             echo "------------------------"
+            
             cd /github/home
             bash benchmarks/scripts/run-performance-benchmarks.sh
             # send the result to es
-            if [[ "${{ github.event_name }}" != "pull request" ]]; then
-              escli add --vllm_branch ${{ matrix.vllm_branch }} \
-              --vllm_ascend_branch ${{ matrix.vllm_ascend_branch }} \
-              --commit_id $commit_id \
-              --commit_title "$commit_title" \
-              --created_at "$commit_time_no_tz" \
-              --res_dir ./benchmarks/results 
-              rm -rf ./benchmarks/results
-            fi
+            escli add --vllm_branch ${{ matrix.vllm_branch }} \
+            --vllm_ascend_branch ${{ matrix.vllm_ascend_branch }} \
+            --commit_id $commit_id \
+            --commit_title "$commit_title" \
+            --created_at "$commit_time_no_tz" \
+            --res_dir ./benchmarks/results \
+            --extra_feat '{"VLLM_USE_V1": "${{ matrix.vllm_use_v1 }}"}'
+            rm -rf ./benchmarks/results
             cd -
           done < commit_log.txt

benchmarks/tests/latency-tests.json

@@ -9,5 +9,15 @@
       "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
+    }
   }
 ]

benchmarks/tests/serving-tests.json

@@ -49,5 +49,29 @@
       "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",
+      "backend": "vllm",
+      "dataset_name": "sharegpt",
+      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
+      "num_prompts": 200
+    }
   }
 ]

benchmarks/tests/throughput-tests.json

@@ -22,6 +22,17 @@
       "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"
+    }
   }
 ]