[CI/UT] Add test for chunk prefill and prefix cache on v1/AscendScheduler (#1505)

### What this PR does / why we need it?
Add test for chunked prefill and prefix cache on v1/AscendScheduler

Covered scenarios:
- `Qwen/Qwen3-0.6B-Base` and `deepseek-ai/DeepSeek-V2-Lite-Chat` ---
multicard CI time increased by 19 min
- `V1 + default scheduler` vs `V1 + default scheduler + enable prefix
cache`
- `V1 + Ascend scheduler` vs `V1 + Ascend scheduler + enable prefix
cache` vs `V1 + Ascend scheduler + enable prefix cache + enable chunked
prefill`
- `Qwen/Qwen3-0.6B-Base` --- singlecard CI time increased by 8 min
- `V1 + Ascend scheduler` vs `V1 + Ascend scheduler + enable chunked
prefill`

should rebase after #1498 and #1446
### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added test.

Signed-off-by: MengqingCao <cmq0113@163.com>

tests/conftest.py

@@ -19,6 +19,7 @@
 
 import contextlib
 import gc
+import os
 from typing import Any, List, Optional, Tuple, TypeVar, Union
 
 import numpy as np
@@ -59,6 +60,9 @@ PromptImageInput = _PromptMultiModalInput[Image.Image]
 PromptAudioInput = _PromptMultiModalInput[Tuple[np.ndarray, int]]
 PromptVideoInput = _PromptMultiModalInput[np.ndarray]
 
+_TEST_DIR = os.path.dirname(__file__)
+_TEST_PROMPTS = [os.path.join(_TEST_DIR, "e2e", "prompts", "example.txt")]
+
 
 def cleanup_dist_env_and_memory(shutdown_ray: bool = False):
     destroy_model_parallel()
@@ -367,6 +371,20 @@ def prompt_template(request):
     return PROMPT_TEMPLATES[request.param]
 
 
+def _read_prompts(filename: str) -> list[str]:
+    with open(filename) as f:
+        prompts = f.readlines()
+        return prompts
+
+
+@pytest.fixture
+def example_prompts() -> list[str]:
+    prompts = []
+    for filename in _TEST_PROMPTS:
+        prompts += _read_prompts(filename)
+    return prompts
+
+
 @pytest.fixture(scope="session")
 def ilama_lora_files():
     return snapshot_download(repo_id="jeeejeee/ilama-text2sql-spider")