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
70 行
2.1 KiB
Python
70 行
2.1 KiB
Python
import subprocess
|
|
import time
|
|
import unittest
|
|
|
|
from sglang.srt.utils import kill_process_tree
|
|
from sglang.test.ci.ci_register import register_cuda_ci
|
|
from sglang.test.kits.eval_accuracy_kit import GSM8KMixin
|
|
from sglang.test.server_fixtures.default_fixture import DefaultServerBase
|
|
|
|
register_cuda_ci(est_time=720, stage="extra-b", runner_config="8-gpu-h200")
|
|
|
|
GLM52_FP8_MODEL_PATH = "zai-org/GLM-5.2-FP8"
|
|
|
|
|
|
class TestGLM52HiSparse(DefaultServerBase, GSM8KMixin):
|
|
"""GLM-5.2 FP8 with HiSparse (host-to-device sparse KV offload) on DSA decode.
|
|
|
|
HiSparse targets the high-concurrency regime and is not used together with
|
|
EAGLE MTP, so this variant runs without speculative decoding (unlike the
|
|
DSA-MTP variants in test_dsa_glm52_{dp,tp}_mtp.py).
|
|
"""
|
|
|
|
model = GLM52_FP8_MODEL_PATH
|
|
other_args = [
|
|
"--trust-remote-code",
|
|
"--tp",
|
|
"8",
|
|
"--dp",
|
|
"8",
|
|
"--enable-dp-attention",
|
|
"--page-size",
|
|
"64",
|
|
"--max-running-requests",
|
|
"200",
|
|
"--mem-fraction-static",
|
|
"0.85",
|
|
"--disable-radix-cache",
|
|
"--kv-cache-dtype",
|
|
"bfloat16",
|
|
"--dsa-decode-backend",
|
|
"flashmla_sparse",
|
|
"--enable-hisparse",
|
|
"--hisparse-config",
|
|
'{"top_k": 2048, "device_buffer_size": 4096, "host_to_device_ratio": 5}',
|
|
"--model-loader-extra-config",
|
|
'{"enable_multithread_load": true, "num_threads": 64}',
|
|
]
|
|
|
|
# Match the original standalone hisparse eval config.
|
|
gsm8k_accuracy_thres = 0.94
|
|
gsm8k_num_questions = 500
|
|
gsm8k_num_threads = 100
|
|
gsm8k_num_shots = 24
|
|
|
|
@classmethod
|
|
def tearDownClass(cls):
|
|
# HiSparse's large pinned host buffer stalls an external SIGKILL teardown
|
|
# (kernel unpin). Drive the server's own graceful shutdown so each rank
|
|
# unregisters in userspace; hard-kill as a fallback.
|
|
cls.process.terminate()
|
|
try:
|
|
cls.process.wait(timeout=90)
|
|
except subprocess.TimeoutExpired:
|
|
kill_process_tree(cls.process.pid, wait_timeout=60)
|
|
time.sleep(2)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|