Write Sglang Test

"""Unit tests for srt/<module>"""

import unittest
from unittest.mock import MagicMock, patch

from sglang.srt.<module> import TargetClass
from sglang.test.ci.ci_register import register_cpu_ci
from sglang.test.test_utils import CustomTestCase

register_cpu_ci(est_time=5, suite="base-a-test-cpu")
# Unit tests are CPU-only. GPU operator tests belong under `kernel/`.

class TestTargetClass(CustomTestCase):
    def test_basic_behavior(self):
        obj = TargetClass(...)
        self.assertEqual(obj.method(), expected)

    @patch("sglang.srt.<module>.some_dependency")
    def test_with_mock(self, mock_dep):
        mock_dep.return_value = MagicMock()
        # test logic with dependency mocked
        ...


if __name__ == "__main__":
    unittest.main()

import unittest

import requests

from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_utils import (
    DEFAULT_SMALL_MODEL_NAME_FOR_TEST,
    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
    DEFAULT_URL_FOR_TEST,
    CustomTestCase,
    popen_launch_server,
    terminate_and_kill_process_tree,
)

register_cuda_ci(est_time=60, stage="base-b", runner_config="1-gpu-small")


class TestMyFeature(CustomTestCase):
    @classmethod
    def setUpClass(cls):
        cls.model = DEFAULT_SMALL_MODEL_NAME_FOR_TEST
        cls.base_url = DEFAULT_URL_FOR_TEST
        cls.process = popen_launch_server(
            cls.model,
            cls.base_url,
            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
            other_args=["--arg1", "value1"],  # feature-specific args
        )

    @classmethod
    def tearDownClass(cls):
        if hasattr(cls, "process") and cls.process:
            terminate_and_kill_process_tree(cls.process)

    def test_basic_functionality(self):
        response = requests.post(
            self.base_url + "/generate",
            json={"text": "Hello", "sampling_params": {"max_new_tokens": 32}},
        )
        self.assertEqual(response.status_code, 200)


if __name__ == "__main__":
    unittest.main(verbosity=3)

import time
import unittest

import requests

from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_utils import (
    DEFAULT_MODEL_NAME_FOR_TEST,
    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
    DEFAULT_URL_FOR_TEST,
    CustomTestCase,
    popen_launch_server,
    terminate_and_kill_process_tree,
)

register_cuda_ci(est_time=300, stage="base-b", runner_config="1-gpu-large")


class TestMyFeaturePerf(CustomTestCase):
    @classmethod
    def setUpClass(cls):
        cls.model = DEFAULT_MODEL_NAME_FOR_TEST
        cls.base_url = DEFAULT_URL_FOR_TEST
        cls.process = popen_launch_server(
            cls.model,
            cls.base_url,
            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
        )

    @classmethod
    def tearDownClass(cls):
        if hasattr(cls, "process") and cls.process:
            terminate_and_kill_process_tree(cls.process)

    def test_latency(self):
        start = time.perf_counter()
        response = requests.post(
            self.base_url + "/generate",
            json={"text": "Hello", "sampling_params": {"max_new_tokens": 128}},
        )
        elapsed = time.perf_counter() - start
        self.assertEqual(response.status_code, 200)
        self.assertLess(elapsed, 5.0, "Latency exceeded threshold")


if __name__ == "__main__":
    unittest.main(verbosity=3)

from sglang.test.server_fixtures.default_fixture import DefaultServerBase

class TestMyFeature(DefaultServerBase):
    model = DEFAULT_SMALL_MODEL_NAME_FOR_TEST
    other_args = ["--enable-my-feature"]

    def test_something(self):
        ...

from sglang.test.ci.ci_register import (
    register_cuda_ci,
    register_amd_ci,
    register_cpu_ci,
    register_npu_ci,
)

# Per-commit test (small 1-gpu, runs on 5090)
register_cuda_ci(est_time=80, stage="base-b", runner_config="1-gpu-small")

# Per-commit test (large 1-gpu, runs on H100)
register_cuda_ci(est_time=120, stage="base-b", runner_config="1-gpu-large")

# Nightly-only test (same shape as per-commit, stage is just "nightly")
register_cuda_ci(est_time=200, stage="nightly", runner_config="1-gpu-large")

# Multi-backend test (only when testing backend-specific code paths)
register_cuda_ci(est_time=80, stage="base-a", runner_config="1-gpu-small")
register_amd_ci(est_time=120, suite="stage-a-test-1-gpu-small-amd")
register_npu_ci(est_time=400, suite="nightly-8-npu-a3", nightly=True)

# Temporarily disabled test
register_cuda_ci(
    est_time=80, stage="base-b", runner_config="1-gpu-small", disabled="flaky - see #12345"
)

from sglang.test.ci.ci_register import register_cuda_ci

# Correctness tests in test/registered/kernels/ops/<group>/
register_cuda_ci(est_time=30, stage="base-b-kernel-unit", runner_config="1-gpu-large")
register_cuda_ci(est_time=30, stage="base-b-kernel-unit", runner_config="4-gpu-b200")
register_cuda_ci(est_time=120, stage="base-b-kernel-unit", runner_config="8-gpu-h200")

# Benchmarks in test/registered/kernels/benchmark/<group>/
register_cuda_ci(est_time=6, stage="base-b-kernel-benchmark", runner_config="1-gpu-large")

# Optional nightly registration — same form, stage is just "nightly"
register_cuda_ci(est_time=120, stage="nightly", runner_config="1-gpu-large")
register_cuda_ci(est_time=120, stage="nightly", runner_config="8-gpu-h200")

test/
├── registered/          # CI tests (auto-discovered by run_suite.py)
│   ├── unit/<subsystem>/      # CPU-only; no server or model weights
│   ├── kernel/<group>/        # accelerator operator correctness/benchmarks
│   ├── e2e/<subsystem>/       # engine/server integration
│   ├── accuracy/<family>/     # scheduled eval floors
│   ├── perf/<family>/         # scheduled latency/throughput contracts
│   └── stress/<subsystem>/    # stress/weekly coverage
├── manual/              # Non-CI: debugging, one-off, manual verification
└── run_suite.py         # CI runner (globs test/registered/**/*.py; nothing outside it)

python/sglang/kernels/jit/   # implementation + test-only helpers, never registered tests

class TestMyFeature(CustomTestCase, MMLUMixin):
    mmlu_score_threshold = 0.65
    mmlu_num_examples = 64
    mmlu_num_threads = 32
    # test_mmlu is inherited — no code needed

from sglang.test.test_utils import (
    CustomTestCase,              # base class with retry logic
    popen_launch_server,         # launch server subprocess
    terminate_and_kill_process_tree,    # SIGTERM, then SIGKILL, then wait for
                                        # the GPU memory to come back
    DEFAULT_URL_FOR_TEST,        # auto-configured base URL
    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,  # 600s default
    run_bench_serving,           # benchmark helper (launch + bench)
)

f=<your new test file>
grep -n "kill_process_tree" $f          # every hit must be terminate_and_kill_process_tree
grep -n "register_.*_ci(" $f            # CUDA: stage= + runner_config=, never suite=
grep -n "CustomTestCase\|unittest.main" $f   # both must appear