97 lines
3.9 KiB
Python
97 lines
3.9 KiB
Python
import os
|
|
import subprocess
|
|
import unittest
|
|
from pathlib import Path
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
|
|
|
|
class EngineContractTest(unittest.TestCase):
|
|
def test_locked_values_match(self) -> None:
|
|
example = (ROOT / "task_info.env.example").read_text(encoding="utf-8")
|
|
workflow_env = (ROOT / ".gitea/workflows/task_info.env").read_text(encoding="utf-8")
|
|
dockerfile = (ROOT / "Dockerfile").read_text(encoding="utf-8")
|
|
self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", example)
|
|
self.assertIn("GPU_TYPE=Iluvatar_bi-150", example)
|
|
self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", workflow_env)
|
|
self.assertIn("GPU_TYPE=Iluvatar_bi-150", workflow_env)
|
|
self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", dockerfile)
|
|
self.assertIn("GPU_TYPE=Iluvatar_bi-150", dockerfile)
|
|
self.assertIn(
|
|
"registry.iluvatar.com.cn:10443/customer/sz/vllm0.17.0-4.4.0-x86:v4.1",
|
|
dockerfile,
|
|
)
|
|
self.assertNotIn("FRAMEWORK=vllm_fix_tokenizer", example)
|
|
self.assertNotIn("FRAMEWORK=vllm_fix_tokenizer", workflow_env)
|
|
self.assertNotIn("FRAMEWORK=vllm_fix_tokenizer", dockerfile)
|
|
|
|
def test_ci_does_not_submit_platform_task(self) -> None:
|
|
workflow = (ROOT / ".gitea/workflows/build.yml").read_text(encoding="utf-8")
|
|
self.assertNotIn("adminApi", workflow)
|
|
self.assertNotIn("modelhub.org.cn", workflow)
|
|
self.assertIn("build-only", workflow)
|
|
self.assertIn('tags:', workflow)
|
|
|
|
def test_no_zip_or_contest_targets(self) -> None:
|
|
makefile = (ROOT / "Makefile").read_text(encoding="utf-8")
|
|
self.assertNotIn("package", makefile)
|
|
self.assertNotIn("submit", makefile)
|
|
self.assertFalse((ROOT / "contest").exists())
|
|
self.assertFalse((ROOT / "computility-run.yaml").exists())
|
|
|
|
def test_dry_run_prints_plan(self) -> None:
|
|
env = os.environ.copy()
|
|
env.pop("FRAMEWORK", None)
|
|
env.pop("GPU_TYPE", None)
|
|
env.pop("MODEL_DIR", None)
|
|
completed = subprocess.run(
|
|
["bash", "scripts/entrypoint.sh", "--dry-run"],
|
|
cwd=ROOT,
|
|
env=env,
|
|
text=True,
|
|
capture_output=True,
|
|
check=False,
|
|
)
|
|
self.assertEqual(completed.returncode, 0, completed.stderr)
|
|
self.assertIn("FRAMEWORK=vllm_0_17_0_corex_4_4_0", completed.stdout)
|
|
self.assertIn("GPU_TYPE=Iluvatar_bi-150", completed.stdout)
|
|
self.assertIn("python3 -m vllm.entrypoints.openai.api_server", completed.stdout)
|
|
self.assertIn("dry-run: 不启动进程，不访问平台", completed.stdout)
|
|
self.assertNotIn("modelhub.org.cn", completed.stdout)
|
|
self.assertIn("<|user|>", completed.stdout)
|
|
|
|
def test_dry_run_rejects_forbidden_framework(self) -> None:
|
|
env = os.environ.copy()
|
|
env["FRAMEWORK"] = "vllm_fix_tokenizer"
|
|
completed = subprocess.run(
|
|
["bash", "scripts/entrypoint.sh", "--dry-run"],
|
|
cwd=ROOT,
|
|
env=env,
|
|
text=True,
|
|
capture_output=True,
|
|
check=False,
|
|
)
|
|
self.assertNotEqual(completed.returncode, 0)
|
|
self.assertIn("vllm_fix_tokenizer", completed.stderr)
|
|
|
|
def test_tokenizer_patch_stays_off(self) -> None:
|
|
import shutil
|
|
import tempfile
|
|
|
|
import apply_patches
|
|
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
model = Path(tmp) / "model"
|
|
shutil.copytree(ROOT / "tests" / "fixtures" / "fake-model", model)
|
|
result = apply_patches.apply_all(
|
|
model,
|
|
(ROOT / "patches/chat_template/default_chat_template.jinja").read_text(encoding="utf-8"),
|
|
apply_patches.load_whitelist(ROOT / "patches/architectures/whitelist.txt"),
|
|
{},
|
|
)
|
|
self.assertFalse(result["tokenizer"]["applied"])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|