[CI][Benchmark] Optimize performance benchmark workflow (#1039)

### What this PR does / why we need it?

This is a post patch of #1014, for some convenience optimization
- Set cached dataset path for speed
- Use pypi to install escli-tool
- Add benchmark results convert script to have a developer-friendly
result
- Patch the `benchmark_dataset.py` to disable streaming load for
internet
- Add more trigger ways for different purpose, `pr` for debug,
`schedule` for daily test, `dispatch` and `pr-labled` for manual testing
of a single(current) commit
- Disable latency test for `qwen-2.5-vl`, (This script does not support
multi-modal yet)

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI passed

---------

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

benchmarks/tests/latency-tests.json

@@ -1,14 +1,4 @@
 [
-  {
-    "test_name": "latency_qwen2_5vl_7B_tp1",
-    "parameters": {
-      "model": "Qwen/Qwen2.5-VL-7B-Instruct",
-      "tensor_parallel_size": 1,
-      "max_model_len": 16384,
-      "num_iters_warmup": 5,
-      "num_iters": 15
-    }
-  },
   {
     "test_name": "latency_qwen3_8B_tp1",
     "parameters": {

benchmarks/tests/serving-tests.json

@@ -46,7 +46,7 @@
       "model": "Qwen/Qwen3-8B",
       "backend": "vllm",
       "dataset_name": "sharegpt",
-      "dataset_path": "/root/.cache/datasets/sharegpt/ShareGPT_V3_unfiltered_cleaned_split.json",
+      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
       "num_prompts": 200
     }
   }

benchmarks/tests/throughput-tests.json

@@ -5,7 +5,7 @@
       "model": "Qwen/Qwen3-8B",
       "tensor_parallel_size": 1,
       "load_format": "dummy",
-      "dataset_path": "/root/.cache/datasets/sharegpt/ShareGPT_V3_unfiltered_cleaned_split.json",
+      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
       "num_prompts": 200,
       "backend": "vllm"
     }