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
92 行
2.4 KiB
Python
92 行
2.4 KiB
Python
"""
|
|
Usage:
|
|
python3 -m unittest test_cpu_graph.TestCPUGraph.test_mmlu_torch_compile_cpu
|
|
"""
|
|
|
|
import copy
|
|
import os
|
|
import unittest
|
|
from types import SimpleNamespace
|
|
|
|
from sglang.srt.utils import get_cpu_ids_by_node, kill_process_tree
|
|
from sglang.test.ci.ci_register import register_cpu_ci
|
|
from sglang.test.run_eval import run_eval
|
|
from sglang.test.test_utils import (
|
|
DEFAULT_MLA_MODEL_NAME_FOR_TEST,
|
|
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
DEFAULT_URL_FOR_TEST,
|
|
CustomTestCase,
|
|
intel_amx_benchmark,
|
|
is_in_ci,
|
|
popen_launch_server,
|
|
)
|
|
|
|
register_cpu_ci(est_time=10, suite="base-b-test-cpu")
|
|
|
|
|
|
class TestCPUGraph(CustomTestCase):
|
|
|
|
@intel_amx_benchmark(
|
|
extra_args=[
|
|
"--batch-size",
|
|
"1",
|
|
"--mem-fraction-static",
|
|
"0.05",
|
|
"--enable-torch-compile",
|
|
"--torch-compile-max-bs",
|
|
"2",
|
|
"--cuda-graph-bs",
|
|
"2",
|
|
],
|
|
min_throughput=7,
|
|
)
|
|
def test_latency_torch_compile_cpu(self):
|
|
return DEFAULT_MLA_MODEL_NAME_FOR_TEST
|
|
|
|
def test_mmlu_torch_compile_cpu(self):
|
|
model = DEFAULT_MLA_MODEL_NAME_FOR_TEST
|
|
base_url = DEFAULT_URL_FOR_TEST
|
|
cpu_ids_by_node = get_cpu_ids_by_node()
|
|
n_numa_node = len(cpu_ids_by_node)
|
|
env = copy.deepcopy(os.environ)
|
|
env["SGLANG_CPU_OMP_THREADS_BIND"] = "all"
|
|
process = popen_launch_server(
|
|
model,
|
|
base_url,
|
|
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
other_args=[
|
|
"--attention-backend",
|
|
"intel_amx",
|
|
"--mem-fraction-static",
|
|
"0.05",
|
|
"--disable-radix",
|
|
"--trust-remote-code",
|
|
"--disable-overlap-schedule",
|
|
"--enable-torch-compile",
|
|
"--cuda-graph-bs",
|
|
"2",
|
|
"--tp",
|
|
f"{n_numa_node}",
|
|
],
|
|
env=env,
|
|
)
|
|
|
|
try:
|
|
args = SimpleNamespace(
|
|
base_url=base_url,
|
|
model=model,
|
|
eval_name="mmlu",
|
|
num_examples=64,
|
|
num_threads=32,
|
|
)
|
|
|
|
metrics = run_eval(args)
|
|
if is_in_ci():
|
|
self.assertGreater(metrics["score"], 0.45)
|
|
finally:
|
|
kill_process_tree(process.pid)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|