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
191 行
6.9 KiB
Python
191 行
6.9 KiB
Python
import json
|
|
import unittest
|
|
|
|
import requests
|
|
|
|
from sglang.srt.utils import kill_process_tree
|
|
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
|
|
from sglang.test.kits.reasoning_kit import (
|
|
ReasoningTokenUsageMixin,
|
|
SeparateReasoningMixin,
|
|
)
|
|
from sglang.test.test_utils import (
|
|
DEFAULT_ENABLE_THINKING_MODEL_NAME_FOR_TEST,
|
|
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
DEFAULT_URL_FOR_TEST,
|
|
CustomTestCase,
|
|
popen_launch_server,
|
|
)
|
|
|
|
register_cuda_ci(est_time=129, stage="base-b", runner_config="1-gpu-large")
|
|
register_amd_ci(est_time=200, suite="stage-b-test-1-gpu-small-amd")
|
|
|
|
|
|
class TestEnableThinking(
|
|
ReasoningTokenUsageMixin, SeparateReasoningMixin, CustomTestCase
|
|
):
|
|
reasoning_parser_name = "qwen3"
|
|
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
cls.model = DEFAULT_ENABLE_THINKING_MODEL_NAME_FOR_TEST
|
|
cls.base_url = DEFAULT_URL_FOR_TEST
|
|
cls.api_key = "sk-1234"
|
|
cls.init_reasoning_token_verifier()
|
|
cls.process = popen_launch_server(
|
|
cls.model,
|
|
cls.base_url,
|
|
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
api_key=cls.api_key,
|
|
other_args=[
|
|
"--reasoning-parser",
|
|
"qwen3",
|
|
],
|
|
)
|
|
cls.additional_chat_kwargs = {}
|
|
|
|
@classmethod
|
|
def tearDownClass(cls):
|
|
kill_process_tree(cls.process.pid)
|
|
|
|
def test_chat_completion_with_reasoning(self):
|
|
# Test non-streaming with "enable_thinking": True, reasoning_content should not be empty
|
|
client = requests.post(
|
|
f"{self.base_url}/v1/chat/completions",
|
|
headers={"Authorization": f"Bearer {self.api_key}"},
|
|
json={
|
|
"model": self.model,
|
|
"messages": [{"role": "user", "content": "Hello"}],
|
|
"temperature": 0,
|
|
"separate_reasoning": True,
|
|
"chat_template_kwargs": {"enable_thinking": True},
|
|
**self.additional_chat_kwargs,
|
|
},
|
|
)
|
|
|
|
self.assertEqual(client.status_code, 200, f"Failed with: {client.text}")
|
|
data = client.json()
|
|
|
|
self.assertIn("choices", data)
|
|
self.assertTrue(len(data["choices"]) > 0)
|
|
self.assertIn("message", data["choices"][0])
|
|
self.assertIn("reasoning_content", data["choices"][0]["message"])
|
|
self.assertIsNotNone(data["choices"][0]["message"]["reasoning_content"])
|
|
|
|
def test_chat_completion_without_reasoning(self):
|
|
# Test non-streaming with "enable_thinking": False, reasoning_content should be empty
|
|
client = requests.post(
|
|
f"{self.base_url}/v1/chat/completions",
|
|
headers={"Authorization": f"Bearer {self.api_key}"},
|
|
json={
|
|
"model": self.model,
|
|
"messages": [{"role": "user", "content": "Hello"}],
|
|
"temperature": 0,
|
|
"separate_reasoning": True,
|
|
"chat_template_kwargs": {"enable_thinking": False},
|
|
**self.additional_chat_kwargs,
|
|
},
|
|
)
|
|
|
|
self.assertEqual(client.status_code, 200, f"Failed with: {client.text}")
|
|
data = client.json()
|
|
|
|
self.assertIn("choices", data)
|
|
self.assertTrue(len(data["choices"]) > 0)
|
|
self.assertIn("message", data["choices"][0])
|
|
|
|
if "reasoning_content" in data["choices"][0]["message"]:
|
|
self.assertIsNone(data["choices"][0]["message"]["reasoning_content"])
|
|
|
|
def test_stream_chat_completion_with_reasoning(self):
|
|
# Test streaming with "enable_thinking": True, reasoning_content should not be empty
|
|
response = requests.post(
|
|
f"{self.base_url}/v1/chat/completions",
|
|
headers={"Authorization": f"Bearer {self.api_key}"},
|
|
json={
|
|
"model": self.model,
|
|
"messages": [{"role": "user", "content": "Hello"}],
|
|
"temperature": 0,
|
|
"separate_reasoning": True,
|
|
"stream": True,
|
|
"chat_template_kwargs": {"enable_thinking": True},
|
|
**self.additional_chat_kwargs,
|
|
},
|
|
stream=True,
|
|
)
|
|
|
|
self.assertEqual(response.status_code, 200, f"Failed with: {response.text}")
|
|
|
|
has_reasoning = False
|
|
has_content = False
|
|
|
|
for line in response.iter_lines():
|
|
if line:
|
|
line = line.decode("utf-8")
|
|
if line.startswith("data:") and not line.startswith("data: [DONE]"):
|
|
data = json.loads(line[6:])
|
|
if "choices" in data and len(data["choices"]) > 0:
|
|
delta = data["choices"][0].get("delta", {})
|
|
|
|
if "reasoning_content" in delta and delta["reasoning_content"]:
|
|
has_reasoning = True
|
|
|
|
if "content" in delta and delta["content"]:
|
|
has_content = True
|
|
|
|
self.assertTrue(
|
|
has_reasoning,
|
|
"The reasoning content is not included in the stream response",
|
|
)
|
|
self.assertTrue(
|
|
has_content, "The stream response does not contain normal content"
|
|
)
|
|
|
|
def test_stream_chat_completion_without_reasoning(self):
|
|
# Test streaming with "enable_thinking": False, reasoning_content should be empty
|
|
response = requests.post(
|
|
f"{self.base_url}/v1/chat/completions",
|
|
headers={"Authorization": f"Bearer {self.api_key}"},
|
|
json={
|
|
"model": self.model,
|
|
"messages": [{"role": "user", "content": "Hello"}],
|
|
"temperature": 0,
|
|
"separate_reasoning": True,
|
|
"stream": True,
|
|
"chat_template_kwargs": {"enable_thinking": False},
|
|
**self.additional_chat_kwargs,
|
|
},
|
|
stream=True,
|
|
)
|
|
|
|
self.assertEqual(response.status_code, 200, f"Failed with: {response.text}")
|
|
|
|
has_reasoning = False
|
|
has_content = False
|
|
|
|
for line in response.iter_lines():
|
|
if line:
|
|
line = line.decode("utf-8")
|
|
if line.startswith("data:") and not line.startswith("data: [DONE]"):
|
|
data = json.loads(line[6:])
|
|
if "choices" in data and len(data["choices"]) > 0:
|
|
delta = data["choices"][0].get("delta", {})
|
|
|
|
if "reasoning_content" in delta and delta["reasoning_content"]:
|
|
has_reasoning = True
|
|
|
|
if "content" in delta and delta["content"]:
|
|
has_content = True
|
|
|
|
self.assertFalse(
|
|
has_reasoning,
|
|
"The reasoning content should not be included in the stream response",
|
|
)
|
|
self.assertTrue(
|
|
has_content, "The stream response does not contain normal content"
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|