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
103 lines
3.3 KiB
Python
103 lines
3.3 KiB
Python
import json
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
|
|
import openai
|
|
import requests
|
|
|
|
|
|
class JSONConstrainedMixin:
|
|
|
|
json_schema = json.dumps(
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"name": {"type": "string", "pattern": "^[\\w]+$"},
|
|
"population": {"type": "integer"},
|
|
},
|
|
"required": ["name", "population"],
|
|
"additionalProperties": False,
|
|
}
|
|
)
|
|
|
|
def _run_decode_json(
|
|
self, json_schema, return_logprob=False, top_logprobs_num=0, n=1
|
|
):
|
|
response = requests.post(
|
|
self.base_url + "/generate",
|
|
json={
|
|
"text": (
|
|
"Introduce the capital of France. Return in a JSON format. The JSON Schema is: "
|
|
+ json.dumps(json_schema)
|
|
),
|
|
"sampling_params": {
|
|
"temperature": 0 if n == 1 else 0.5,
|
|
"max_new_tokens": 128,
|
|
"n": n,
|
|
"stop_token_ids": [119690],
|
|
"json_schema": json_schema,
|
|
},
|
|
"stream": False,
|
|
"return_logprob": return_logprob,
|
|
"top_logprobs_num": top_logprobs_num,
|
|
"logprob_start_len": 0,
|
|
},
|
|
)
|
|
ret = response.json()
|
|
print(json.dumps(ret))
|
|
print("=" * 100)
|
|
|
|
if not json_schema or json_schema == "INVALID":
|
|
return
|
|
|
|
# Make sure the json output is valid
|
|
try:
|
|
js_obj = json.loads(ret["text"])
|
|
except (TypeError, json.decoder.JSONDecodeError):
|
|
raise
|
|
|
|
self.assertIsInstance(js_obj["name"], str)
|
|
self.assertIsInstance(js_obj["population"], int)
|
|
|
|
def test_json_generate(self):
|
|
self._run_decode_json(json_schema=self.json_schema)
|
|
|
|
def test_json_invalid(self):
|
|
self._run_decode_json(json_schema="INVALID")
|
|
|
|
def test_json_openai(self):
|
|
client = openai.Client(api_key="EMPTY", base_url=f"{self.base_url}/v1")
|
|
|
|
response = client.chat.completions.create(
|
|
model=self.model,
|
|
messages=[
|
|
{"role": "system", "content": "You are a helpful AI assistant"},
|
|
{
|
|
"role": "user",
|
|
"content": "Introduce the capital of France. Return in a JSON format. "
|
|
"The JSON Schema is: " + json.dumps(self.json_schema),
|
|
},
|
|
],
|
|
temperature=0,
|
|
max_tokens=128,
|
|
response_format={
|
|
"type": "json_schema",
|
|
"json_schema": {"name": "foo", "schema": json.loads(self.json_schema)},
|
|
},
|
|
)
|
|
text = response.choices[0].message.content
|
|
|
|
try:
|
|
js_obj = json.loads(text)
|
|
except (TypeError, json.decoder.JSONDecodeError):
|
|
print("JSONDecodeError", text)
|
|
raise
|
|
|
|
self.assertIsInstance(js_obj["name"], str)
|
|
self.assertIsInstance(js_obj["population"], int)
|
|
|
|
def test_mix_json_and_other(self):
|
|
json_schemas = [None, None, self.json_schema, self.json_schema] * 10
|
|
|
|
with ThreadPoolExecutor(len(json_schemas)) as executor:
|
|
list(executor.map(self._run_decode_json, json_schemas))
|