72 lines
2.7 KiB
Python
72 lines
2.7 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
|
|
|
|
"""
|
|
Qwen-Image stability: OmniServer (diffusion) + ``diffusion_benchmark_serving.py``.
|
|
|
|
Configuration: ``tests/dfx/stability/tests/test_qwen_image.json``.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from tests.dfx.conftest import (
|
|
create_benchmark_indices,
|
|
create_test_parameter_mapping,
|
|
create_unique_server_pytest_params,
|
|
load_configs,
|
|
)
|
|
from tests.dfx.stability.helpers import _run_one_diffusion_batch, run_stability_benchmark_loop
|
|
|
|
STABILITY_DIR = Path(__file__).resolve().parent.parent
|
|
DEPLOY_CONFIGS_DIR = STABILITY_DIR / "deploy"
|
|
CONFIG_FILE_PATH = str(STABILITY_DIR / "tests" / "test_qwen_image.json")
|
|
DEFAULT_NUM_PROMPTS_PER_BATCH = 20
|
|
STABILITY_SERVER_TIMEOUT_ARGS = ["--stage-init-timeout", "600", "--init-timeout", "900"]
|
|
|
|
try:
|
|
BENCHMARK_CONFIGS = load_configs(CONFIG_FILE_PATH)
|
|
except FileNotFoundError:
|
|
BENCHMARK_CONFIGS = []
|
|
|
|
test_params = create_unique_server_pytest_params(BENCHMARK_CONFIGS, DEPLOY_CONFIGS_DIR) if BENCHMARK_CONFIGS else []
|
|
server_to_benchmark_mapping = create_test_parameter_mapping(BENCHMARK_CONFIGS) if BENCHMARK_CONFIGS else {}
|
|
benchmark_indices = create_benchmark_indices(BENCHMARK_CONFIGS, server_to_benchmark_mapping)
|
|
|
|
|
|
# Pytest marks (hardware, local_model, slow, diffusion) come from test_qwen_image.json.
|
|
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
|
|
@pytest.mark.parametrize("stability_benchmark_params", benchmark_indices, indirect=True)
|
|
def test_stability_qwen_image(omni_server, stability_benchmark_params):
|
|
test_name = stability_benchmark_params["test_name"]
|
|
params = stability_benchmark_params["params"]
|
|
duration_sec = params.get("duration_sec", 300)
|
|
num_prompts_per_batch = params.get("num_prompts_per_batch", DEFAULT_NUM_PROMPTS_PER_BATCH)
|
|
request_rate = params.get("request_rate")
|
|
max_concurrency = params.get("max_concurrency")
|
|
|
|
bench_params = {
|
|
k: v
|
|
for k, v in params.items()
|
|
if k not in ("duration_sec", "request_rate", "max_concurrency", "num_prompts_per_batch")
|
|
}
|
|
|
|
result = run_stability_benchmark_loop(
|
|
host=omni_server.host,
|
|
port=omni_server.port,
|
|
model=omni_server.model,
|
|
duration_sec=duration_sec,
|
|
params=bench_params,
|
|
request_rate=request_rate,
|
|
max_concurrency=max_concurrency,
|
|
result_dir=str(STABILITY_DIR),
|
|
num_prompts_per_batch=num_prompts_per_batch,
|
|
run_one_batch=_run_one_diffusion_batch,
|
|
)
|
|
|
|
assert result.get("failed", 0) == 0, f"[{test_name}] Failed requests detected: {result.get('errors', [])}"
|
|
assert result.get("completed", 0) > 0, f"[{test_name}] No requests completed"
|