docker run -it --net=host \
--name=vllm_test \
--privileged=true \
--device=/dev/upgrade:/dev/upgrade \
--device=/dev/davinci0:/dev/davinci0 \
--device=/dev/davinci_manager \
-v /etc/sys_version.conf:/etc/sys_version.conf \
-v /etc/ld.so.conf.d/mind_so.conf:/etc/ld.so.conf.d/mind_so.conf \
-v /etc/hdcBasic.cfg:/etc/hdcBasic.cfg \
-v /var/dmp_daemon:/var/dmp_daemon \
-v /usr/lib64/libsemanage.so.2:/usr/lib64/libsemanage.so.2 \
-v /usr/lib64/libmmpa.so:/usr/lib64/libmmpa.so \
-v /usr/lib64/libcrypto.so.1.1:/usr/lib64/libcrypto.so.1.1 \
-v /usr/lib64/libyaml-0.so.2.0.9:/usr/lib64/libyaml-0.so.2 \
-v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi \
-v /usr/lib64/libstackcore.so:/usr/lib64/libstackcore.so \
-v /etc/slog.conf:/etc/slog.conf \
-v /var/slogd:/var/slogd \
-v /usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64 \
-v /home/xiaojiangwu:/home/xiaojiangwu \
a6be1f66f70f /bin/bash;

# 容器内执行
rm -rf /var/log/npu/slog
export ASCEND_GLOBAL_LOG_LEVEL=0
dmesg -c
# 执行某程序。。。
tar -zcvf slog.tar.gz /var/log/npu/slog
dmesg -T > mesg.log

msnpureport -f # 物理机执行

# 安装python==3.10.12
wet https://www.python.org/ftp/python/3.10.12/Python-3.10.12.tgz --no-check-certificate
gzip -d Python-3.10.12.tgz && tar -xvf Python-3.10.12.tar

cd Python-3.10.12 && ./configure --prefix=/usr/local/python3.10.12 --enable-loadable-sqlite-extensions --enable-shared

make && make install

vim /run.sh # 追加如下

export LD_LIBRARY_PATH=/usr/local/python3.10.12/lib:$LD_LIBRARY_PATH
export PATH=/usr/local/python3.10.12/bin:$PATH

source /run.sh

which python3

ln -sf /usr/local/python3.10.12/bin/python3 /usr/local/python3.10.12/bin/python # 使能python命令

# 设置构建参数
PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
COMPILE_CUSTOM_KERNELS=1

# 设置环境变量
export DEBIAN_FRONTEND=noninteractive
export COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}



# 更新包列表并安装依赖
apt-get update -y && \
apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev && \
rm -rf /var/cache/apt/* && \
rm -rf /var/lib/apt/lists/*

# 配置pip源
pip config set global.index-url ${PIP_INDEX_URL}

# https://github.com/vllm-project/vllm
# https://github.com/vllm-project/vllm-ascend
# 克隆vLLM仓库【注意以上vllm与vllm-ascend链接里的版本必须保持一致】 
VLLM_REPO=https://github.com/vllm-project/vllm.git
VLLM_TAG=v0.10.0
git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
cd /vllm-workspace/vllm

# 安装vLLM并卸载triton
VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip uninstall -y triton && \
python3 -m pip cache purge




# 设置昇腾环境并安装vllm-ascend
VLLM_ASCEND_REPO=https://github.com/vllm-project/vllm-ascend.git
VLLM_ASCEND_TAG=v0.10.0rc1
git clone --depth 1 $VLLM_ASCEND_REPO --branch $VLLM_ASCEND_TAG /vllm-workspace/vllm-ascend
cd /vllm-workspace/vllm-ascend

export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
source /usr/local/Ascend/ascend-toolkit/set_env.sh
source /usr/local/Ascend/nnal/atb/set_env.sh
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib
export SOC_VERSION=ASCEND310P1

python3.10 -m pip install --upgrade pip
python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/
python3 -m pip cache purge

export ASCEND_GLOBAL_LOG_LEVEL=1
export ASCEND_HOST_FILE_NUM=1000
export ASCEND_DEVICE_FLUSH_TIMEOUT=5000
export ASCEND_SLOG_PRINT_TO_STDOUT=1

from vllm import LLM, SamplingParams

prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]

# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
# Create an LLM.
llm = LLM(model="/home/xiaojiangwu/uploaded_files/weights/Qwen3-1.7B", enforce_eager=True, dtype="float16", max_model_len=100)

# Generate texts from the prompts.
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")