4970de4242
### What this PR does / why we need it?
Enable the tests that were skipped due to an outdated driver version:
- tests/e2e/multicard/4-cards/long_sequence/test_accuracy.py
- tests/e2e/multicard/4-cards/long_sequence/test_basic.py
- tests/e2e/multicard/4-cards/long_sequence/test_chunked_prefill.py
and some cases in
- tests/e2e/multicard/2-cards/spec_decode/test_spec_decode.py
- tests/e2e/multicard/2-cards/test_external_launcher.py
- tests/e2e/multicard/2-cards/test_offline_weight_load.py
- tests/e2e/multicard/2-cards/test_quantization.py
- tests/e2e/multicard/4-cards/test_data_parallel_tp2.py
TODO:
- tests/e2e/multicard/4-cards/spec_decode/test_mtp_qwen3_next.py
- tests/e2e/multicard/4-cards/long_sequence/test_mtp.py
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.0
- vLLM main:
d68209402d
Signed-off-by: wjunLu <wjunlu217@gmail.com>
75 lines
1.9 KiB
Python
75 lines
1.9 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# Copyright 2023 The vLLM team.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
"""
|
|
Run `pytest tests/multicard/test_offline_load_weight.py`.
|
|
"""
|
|
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
MODELS = ["Qwen/Qwen3-30B-A3B"]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
|
|
def test_qwen3_offline_load_and_sleepmode_tp2(model):
|
|
script = Path(
|
|
__file__
|
|
).parent.parent.parent.parent.parent / "examples" / "offline_external_launcher.py"
|
|
env = os.environ.copy()
|
|
cmd = [
|
|
sys.executable,
|
|
str(script),
|
|
"--model",
|
|
model,
|
|
"--tp-size",
|
|
"2",
|
|
"--node-size",
|
|
"1",
|
|
"--node-rank",
|
|
"0",
|
|
"--proc-per-node",
|
|
"2",
|
|
"--trust-remote-code",
|
|
"--enable-sleep-mode",
|
|
"--temperature",
|
|
"0",
|
|
"--model-weight-gib",
|
|
"0.8",
|
|
]
|
|
|
|
print(f"Running subprocess: {' '.join(cmd)}")
|
|
proc = subprocess.run(
|
|
cmd,
|
|
env=env,
|
|
stdout=subprocess.PIPE,
|
|
stderr=subprocess.STDOUT,
|
|
timeout=600,
|
|
)
|
|
output = proc.stdout.decode(errors='ignore')
|
|
|
|
print(output)
|
|
|
|
assert "Generated text:" in output
|
|
assert "Sleep and wake up successfully!!" in output
|
|
assert proc.returncode == 0
|