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
129 行
4.3 KiB
Python
129 行
4.3 KiB
Python
"""Unit test for benchmark/hicache/bench_long_context.py.
|
|
|
|
Guards against the regression where ContextWorkloadGenerator.__init__ replaces
|
|
WorkloadGenerator.__init__ entirely but forgets to set attributes the inherited
|
|
request_sender/handle_request methods need (e.g. self.request_func).
|
|
"""
|
|
|
|
import json
|
|
import sys
|
|
import tempfile
|
|
import unittest
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
from sglang.test.ci.ci_register import register_cpu_ci
|
|
from sglang.test.test_utils import CustomTestCase
|
|
|
|
register_cpu_ci(est_time=5, suite="base-a-test-cpu")
|
|
|
|
REPO_ROOT = Path(__file__).resolve().parents[3]
|
|
HICACHE_DIR = REPO_ROOT / "benchmark" / "hicache"
|
|
if str(HICACHE_DIR) not in sys.path:
|
|
sys.path.insert(0, str(HICACHE_DIR))
|
|
|
|
import bench_long_context # noqa: E402
|
|
|
|
from sglang.test.kits.cache_hit_kit import async_request_sglang_generate # noqa: E402
|
|
|
|
|
|
def _build_args(dataset_path: str) -> SimpleNamespace:
|
|
return SimpleNamespace(
|
|
host="localhost",
|
|
port=30000,
|
|
model_path="meta-llama/Llama-3.2-1B-Instruct",
|
|
distribution="poisson",
|
|
request_rate=1.0,
|
|
dataset_path=dataset_path,
|
|
num_clients=2,
|
|
max_parallel=2,
|
|
log_file="performance_metrics.jsonl",
|
|
tag="",
|
|
)
|
|
|
|
|
|
def _fake_dataset() -> dict:
|
|
return {
|
|
"contexts": ["ctx-zero ", "ctx-one "],
|
|
"queries": [
|
|
{"context": 0, "question": "q0", "reference_answer": "a0"},
|
|
{"context": 1, "question": "q1", "reference_answer": "a1"},
|
|
],
|
|
}
|
|
|
|
|
|
class TestContextWorkloadGeneratorInit(CustomTestCase):
|
|
"""Verify ContextWorkloadGenerator wires up everything its inherited
|
|
request_sender/handle_request/run methods rely on."""
|
|
|
|
def setUp(self):
|
|
self._tmp = tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False)
|
|
json.dump(_fake_dataset(), self._tmp)
|
|
self._tmp.close()
|
|
self.dataset_path = self._tmp.name
|
|
|
|
mock_tokenizer = MagicMock()
|
|
mock_tokenizer.encode.return_value = [1, 2, 3, 4]
|
|
mock_tokenizer.return_value = {"input_ids": [5, 6]}
|
|
|
|
self._tok_patch = patch.object(
|
|
bench_long_context, "get_tokenizer", return_value=mock_tokenizer
|
|
)
|
|
self._tok_patch.start()
|
|
|
|
def tearDown(self):
|
|
self._tok_patch.stop()
|
|
Path(self.dataset_path).unlink(missing_ok=True)
|
|
|
|
def test_request_func_is_set(self):
|
|
"""The bug we're guarding against: request_func not being set caused
|
|
AttributeError as soon as the request_sender thread fired."""
|
|
gen = bench_long_context.ContextWorkloadGenerator(
|
|
_build_args(self.dataset_path)
|
|
)
|
|
self.assertTrue(callable(getattr(gen, "request_func", None)))
|
|
self.assertIs(gen.request_func, async_request_sglang_generate)
|
|
|
|
def test_inherits_workload_generator_contract(self):
|
|
"""All attributes WorkloadGenerator's run-time methods touch must exist."""
|
|
gen = bench_long_context.ContextWorkloadGenerator(
|
|
_build_args(self.dataset_path)
|
|
)
|
|
|
|
# handle_request (bench_multiturn.py) reads these
|
|
for attr in ("request_func", "url", "pbar", "response_queue", "finished_time"):
|
|
self.assertTrue(hasattr(gen, attr), f"missing attribute: {attr}")
|
|
|
|
# request_sender reads these
|
|
for attr in (
|
|
"sent_requests",
|
|
"completed_requests",
|
|
"max_parallel",
|
|
"ready_queue",
|
|
"distribution",
|
|
"request_rate",
|
|
):
|
|
self.assertTrue(hasattr(gen, attr), f"missing attribute: {attr}")
|
|
|
|
# run() reads these
|
|
for attr in ("performance_metrics", "enable_round_barrier"):
|
|
self.assertTrue(hasattr(gen, attr), f"missing attribute: {attr}")
|
|
|
|
def test_url_targets_sglang_generate_endpoint(self):
|
|
gen = bench_long_context.ContextWorkloadGenerator(
|
|
_build_args(self.dataset_path)
|
|
)
|
|
self.assertEqual(gen.url, "http://localhost:30000/generate")
|
|
|
|
def test_ready_queue_size_matches_dataset(self):
|
|
gen = bench_long_context.ContextWorkloadGenerator(
|
|
_build_args(self.dataset_path)
|
|
)
|
|
# 2 queries in fake dataset, num_clients=2 → 2 init requests
|
|
self.assertEqual(len(gen.ready_queue.requests), 2)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|