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
101 行
3.3 KiB
Python
101 行
3.3 KiB
Python
import json
|
|
import os
|
|
import tempfile
|
|
import unittest
|
|
from unittest.mock import patch
|
|
|
|
from sglang.srt.server_args import ServerArgs
|
|
from sglang.test.ci.ci_register import register_cpu_ci
|
|
|
|
register_cpu_ci(est_time=10, suite="base-b-test-cpu")
|
|
register_cpu_ci(est_time=10, suite="base-b-test-cpu-arm64")
|
|
|
|
|
|
class TestServerArgsCPUBackend(unittest.TestCase):
|
|
def _make_server_args(self, attention_backend=None):
|
|
server_args = ServerArgs.__new__(ServerArgs)
|
|
server_args.device = "cpu"
|
|
server_args.attention_backend = attention_backend
|
|
server_args.sampling_backend = None
|
|
return server_args
|
|
|
|
@patch("sglang.srt.server_args.is_host_cpu_arm64", return_value=True)
|
|
def test_arm_cpu_defaults_to_torch_native(self, _mock_is_arm64):
|
|
server_args = self._make_server_args()
|
|
|
|
ServerArgs._handle_cpu_backends(server_args)
|
|
|
|
self.assertEqual(server_args.attention_backend, "torch_native")
|
|
self.assertEqual(server_args.sampling_backend, "pytorch")
|
|
|
|
@patch("sglang.srt.server_args.is_host_cpu_arm64", return_value=False)
|
|
def test_x86_cpu_defaults_to_intel_amx(self, _mock_is_arm64):
|
|
server_args = self._make_server_args()
|
|
|
|
ServerArgs._handle_cpu_backends(server_args)
|
|
|
|
self.assertEqual(server_args.attention_backend, "intel_amx")
|
|
self.assertEqual(server_args.sampling_backend, "pytorch")
|
|
|
|
|
|
class TestServerArgsIBDeviceValidation(unittest.TestCase):
|
|
def _validate_ib_devices(self, device_str, available_devices=None):
|
|
server_args = ServerArgs.__new__(ServerArgs)
|
|
available_devices = available_devices or [
|
|
"mlx5_0",
|
|
"mlx5_1",
|
|
"mlx5_2",
|
|
"mlx5_3",
|
|
]
|
|
real_isdir = os.path.isdir
|
|
real_listdir = os.listdir
|
|
|
|
with patch(
|
|
"sglang.srt.server_args.os.path.isdir",
|
|
side_effect=lambda path: (
|
|
True if path == "/sys/class/infiniband" else real_isdir(path)
|
|
),
|
|
), patch(
|
|
"sglang.srt.server_args.os.listdir",
|
|
side_effect=lambda path: (
|
|
available_devices
|
|
if path == "/sys/class/infiniband"
|
|
else real_listdir(path)
|
|
),
|
|
):
|
|
return ServerArgs._validate_ib_devices(server_args, device_str)
|
|
|
|
def test_validate_ib_devices_accepts_comma_separated(self):
|
|
self.assertEqual(
|
|
self._validate_ib_devices("mlx5_0, mlx5_1"),
|
|
"mlx5_0,mlx5_1",
|
|
)
|
|
|
|
def test_validate_ib_devices_accepts_json_object(self):
|
|
result = self._validate_ib_devices(
|
|
'{"0": "mlx5_0, mlx5_1", "1": "mlx5_2, mlx5_3"}'
|
|
)
|
|
self.assertEqual(
|
|
json.loads(result),
|
|
{"0": "mlx5_0,mlx5_1", "1": "mlx5_2,mlx5_3"},
|
|
)
|
|
|
|
def test_validate_ib_devices_accepts_json_file(self):
|
|
with tempfile.NamedTemporaryFile("w", suffix=".json", delete=False) as file:
|
|
json.dump({"0": "mlx5_0, mlx5_1", "1": "mlx5_2"}, file)
|
|
json_file = file.name
|
|
|
|
try:
|
|
result = self._validate_ib_devices(json_file)
|
|
finally:
|
|
os.unlink(json_file)
|
|
|
|
self.assertEqual(
|
|
json.loads(result),
|
|
{"0": "mlx5_0,mlx5_1", "1": "mlx5_2"},
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|