项目文件夹

文件
wehub-resource-sync 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
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

109 行
3.7 KiB
Python

import os
import subprocess
from abc import ABC
from types import SimpleNamespace
from sglang.srt.utils import kill_process_tree
from sglang.test.ascend.test_ascend_utils import write_results_to_github_step_summary
from sglang.test.run_eval import run_eval
from sglang.test.test_utils import (
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
DEFAULT_URL_FOR_TEST,
popen_launch_server,
write_github_step_summary,
)
class GSM8KAscendMixin(ABC):
model = ""
timeout_for_server_launch = DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH
other_args = [
"--trust-remote-code",
"--mem-fraction-static",
"0.8",
"--attention-backend",
"ascend",
"--disable-cuda-graph",
]
server_cmd = ""
gsm8k_num_shots = 5
num_questions = 200
gsm8k_parallel = 128
env = {
**os.environ,
"PYTORCH_NPU_ALLOC_CONF": "expandable_segments:True",
"ASCEND_MF_STORE_URL": "tcp://127.0.0.1:24666",
"HCCL_BUFFSIZE": "200",
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK": "24",
"USE_VLLM_CUSTOM_ALLREDUCE": "1",
"HCCL_EXEC_TIMEOUT": "200",
"STREAMS_PER_DEVICE": "32",
"SGLANG_ENBLE_TORCH_COMILE": "1",
"AUTO_USE_UC_MEMORY": "0",
"P2P_HCCL_BUFFSIZE": "20",
}
@classmethod
def setUpClass(cls):
cls.base_url = DEFAULT_URL_FOR_TEST
try:
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=cls.timeout_for_server_launch,
other_args=cls.other_args,
env=cls.env,
)
cls.server_cmd = subprocess.list2cmdline(cls.process.args)
except Exception as e:
write_github_step_summary(f"Failed to launch server for {cls.model}: {e}")
raise AssertionError(f"Test failed for {cls.model}: {e}")
@classmethod
def tearDownClass(cls):
kill_process_tree(cls.process.pid)
def test_gsm8k(self):
accuracy_threshold = getattr(self, "accuracy", 0.00)
output_throughput_threshold = getattr(self, "output_throughput", 0.00)
model_metrics = {
"server": self.server_cmd,
"client": "few_shot_gsm8k",
"accuracy_threshold": getattr(self, "accuracy", "N/A"),
"output_throughput_threshold": getattr(self, "output_throughput", "N/A"),
}
try:
args = SimpleNamespace(
max_tokens=512,
base_url=self.base_url,
model=self.model,
eval_name="gsm8k",
api="completion",
num_examples=self.num_questions,
num_threads=128,
num_shots=self.gsm8k_num_shots,
)
metrics = run_eval(args)
model_metrics["accuracy"] = metrics["score"]
model_metrics["output_throughput"] = metrics["output_throughput"]
model_metrics["latency"] = metrics["latency"]
self.assertGreaterEqual(
metrics["score"],
accuracy_threshold,
f'Accuracy of {self.model} is {str(metrics["score"])}, is lower than {accuracy_threshold}',
)
self.assertGreaterEqual(
metrics["output_throughput"],
output_throughput_threshold,
f'Output throughput of {self.model} is {str(metrics["output_throughput"])}, is lower than {output_throughput_threshold}',
)
except Exception as e:
model_metrics["error"] = e
self.fail(f"Test failed for {self.model}: {e}")
finally:
write_results_to_github_step_summary({self.model: model_metrics})