sgl-project--sglang
94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
112 行
2.9 KiB
Python
112 行
2.9 KiB
Python
import unittest
|
|
from types import SimpleNamespace
|
|
|
|
from sglang.test.ci.ci_register import register_cuda_ci
|
|
from sglang.test.run_eval import run_eval
|
|
from sglang.test.test_utils import (
|
|
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
DEFAULT_URL_FOR_TEST,
|
|
CustomTestCase,
|
|
kill_process_tree,
|
|
popen_launch_server,
|
|
)
|
|
|
|
register_cuda_ci(est_time=600, stage="extra-b", runner_config="4-gpu-h100")
|
|
|
|
QWEN3_MOE_MODEL_PATH = "Qwen/Qwen3-30B-A3B-FP8"
|
|
|
|
GSM8K_BASELINE_ACCURACY = 0.93
|
|
|
|
|
|
class _Qwen3MoePPCompatMixin:
|
|
"""Launch a Qwen3 MoE server combining PP with another parallel strategy and
|
|
check GSM8K accuracy. Concrete subclasses set ``parallel_args`` (and
|
|
optionally ``server_env``); this mixin is not a TestCase so it is never
|
|
collected on its own.
|
|
"""
|
|
|
|
model = QWEN3_MOE_MODEL_PATH
|
|
parallel_args: list = []
|
|
server_env = None
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
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=[
|
|
*cls.parallel_args,
|
|
"--cuda-graph-max-bs-decode",
|
|
"32",
|
|
"--max-running-requests",
|
|
"32",
|
|
"--trust-remote-code",
|
|
"--disable-piecewise-cuda-graph",
|
|
"--model-loader-extra-config",
|
|
'{"enable_multithread_load": true, "num_threads": 64}',
|
|
],
|
|
env=cls.server_env,
|
|
)
|
|
|
|
@classmethod
|
|
def tearDownClass(cls):
|
|
if hasattr(cls, "process") and cls.process:
|
|
kill_process_tree(cls.process.pid)
|
|
|
|
def test_gsm8k(self):
|
|
args = SimpleNamespace(
|
|
model=self.model,
|
|
eval_name="gsm8k",
|
|
num_shots=5,
|
|
num_examples=200,
|
|
max_tokens=16000,
|
|
num_threads=128,
|
|
repeat=1,
|
|
temperature=0.6,
|
|
top_p=0.95,
|
|
top_k=20,
|
|
base_url=self.base_url,
|
|
)
|
|
metrics = run_eval(args)
|
|
print(f"{metrics=}")
|
|
self.assertGreaterEqual(metrics["score"], GSM8K_BASELINE_ACCURACY)
|
|
|
|
|
|
class TestQwen3MoePPxCP(_Qwen3MoePPCompatMixin, CustomTestCase):
|
|
"""PP x CP: pp_size=2 x attn_cp_size=2 (tp_size=2, moe_dp_size=1)."""
|
|
|
|
parallel_args = [
|
|
"--tp-size",
|
|
"2",
|
|
"--pp-size",
|
|
"2",
|
|
"--ep-size",
|
|
"2",
|
|
"--attn-cp-size",
|
|
"2",
|
|
"--enable-prefill-cp",
|
|
"--cp-strategy",
|
|
"zigzag",
|
|
]
|
|
server_env = {"SGLANG_ENABLE_CP_V2": "1"}
|
|
|
|
|
|
class TestQwen3MoePPxDP(_Qwen3MoePPCompatMixin, CustomTestCase):
|
|
"""PP x DP: pp_size=2 x dp_size=2 attention (tp_size=2)."""
|
|
|
|
parallel_args = [
|
|
"--tp-size",
|
|
"2",
|
|
"--pp-size",
|
|
"2",
|
|
"--dp-size",
|
|
"2",
|
|
"--enable-dp-attention",
|
|
]
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|