a1f142b7ad
There is a lot hack code for v0.11.0, which makes the code hard to
upgrade to newer vLLM version. Since v0.11.0 will release soon. Let's
drop v0.11.0 support first. Then we'll upgrade to v0.11.2 soon.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
58 lines
1.9 KiB
Python
58 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.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
|
|
import os
|
|
|
|
import torch
|
|
from vllm import LLM, SamplingParams
|
|
from vllm.utils.mem_constants import GiB_bytes
|
|
|
|
os.environ["VLLM_USE_MODELSCOPE"] = "True"
|
|
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
|
|
|
|
def main():
|
|
prompt = "How are you?"
|
|
|
|
free, total = torch.npu.mem_get_info()
|
|
print(f"Free memory before sleep: {free / 1024 ** 3:.2f} GiB")
|
|
# record npu memory use baseline in case other process is running
|
|
used_bytes_baseline = total - free
|
|
llm = LLM("Qwen/Qwen2.5-0.5B-Instruct", enable_sleep_mode=True)
|
|
sampling_params = SamplingParams(temperature=0, max_tokens=10)
|
|
output = llm.generate(prompt, sampling_params)
|
|
|
|
llm.sleep(level=1)
|
|
|
|
free_npu_bytes_after_sleep, total = torch.npu.mem_get_info()
|
|
print(
|
|
f"Free memory after sleep: {free_npu_bytes_after_sleep / 1024 ** 3:.2f} GiB"
|
|
)
|
|
used_bytes = total - free_npu_bytes_after_sleep - used_bytes_baseline
|
|
# now the memory usage should be less than the model weights
|
|
# (0.5B model, 1GiB weights)
|
|
assert used_bytes < 1 * GiB_bytes
|
|
|
|
llm.wake_up()
|
|
output2 = llm.generate(prompt, sampling_params)
|
|
# cmp output
|
|
assert output[0].outputs[0].text == output2[0].outputs[0].text
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|