00000389
rmmod iluvatar
sudo /usr/local/corex/bin/corex-driver-uninstaller
sudo /usr/local/corex/bin/corex-uninstaller
ls -l /usr/local/corex*
确保/usr/local/ 下没有corex开头的目录
在sftp上下载需要的安装包
通过SFTP下载:
sftp -P 29880 iluvatar_mr@iftp.iluvatar.com.cn
SFTP用户名和密码,请联系天数售后工程师获取
source /root/.bashrc
检查是否安装成功
ixsmi
apt-get install git-lfs 或者yum install git-lfs
mkdir -p /home/Qwen/
cd /home/Qwen/
git clone https://www.modelscope.cn/Qwen/Qwen3-4B.git
git clone https://www.modelscope.cn/Qwen/Qwen3-8B.git
git clone https://www.modelscope.cn/Qwen/Qwen3-14B.git
git clone https://www.modelscope.cn/Qwen/Qwen3-32B.git
docker pull harbor.iluvatar.com.cn:10443/saas/bi100-3.2.3-aarch64-ubuntu20.04-py3.10-poc-llm-infer:v1.2.3
docker run -dit -v /usr/src:/usr/src -v /lib/modules:/lib/modules -v /dev:/dev -v /home:/home --network=host --name=Qwen3 --ipc=host --privileged --cap-add=ALL --pid=host harbor.iluvatar.com.cn:10443/saas/bi100-3.2.3-aarch64-ubuntu20.04-py3.10-poc-llm-infer:v1.2.3 /bin/bash
进入容器
docker exec -it Qwen3 bash
cd /root/apps/llm-modelzoo/inference/Qwen/vllm
python3 offline_inference.py --model /home/Qwen/Qwen3-4B/ --max-tokens 256 --temperature 0.0 --max-model-len 3096
python3 offline_inference.py --model /home/Qwen/Qwen3-8B/ --max-tokens 256 --temperature 0.0 --max-model-len 3096
python3 offline_inference.py --model /home/Qwen/Qwen3-14B/ --max-tokens 256 -tp 2 --temperature 0.0 --max-model-len 3096
python3 offline_inference.py --model /home/Qwen/Qwen3-32B/ --max-tokens 256 -tp 4 --temperature 0.0 --max-model-len 3096
# server 端
python3 -m vllm.entrypoints.openai.api_server --model /home/Qwen/Qwen3-4B/ --gpu-memory-utilization 0.9 --max-num-batched-tokens 5120 --max-model-len 2048 --max-num-seqs 256 --host 0.0.0.0 --port 1234 --trust-remote-code
python3 -m vllm.entrypoints.openai.api_server --model /home/Qwen/Qwen3-8B/ --gpu-memory-utilization 0.9 --max-num-batched-tokens 5120 --max-model-len 2048 --max-num-seqs 256 --host 0.0.0.0 --port 1234 --trust-remote-code
python3 -m vllm.entrypoints.openai.api_server --model /home/Qwen/Qwen3-14B/ --gpu-memory-utilization 0.9 --max-num-batched-tokens 5120 --max-model-len 2048 --max-num-seqs 256 -tp 2 --host 0.0.0.0 --port 1234 --trust-remote-code
python3 -m vllm.entrypoints.openai.api_server --model /home/Qwen/Qwen3-32B/ --gpu-memory-utilization 0.9 --max-num-batched-tokens 5120 --max-model-len 2048 --max-num-seqs 256 -tp 4 --host 0.0.0.0 --port 1234 --trust-remote-code
# client 端
curl -X POST http://0.0.0.0:1234/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{"model": "/home/Qwen/Qwen3-4B/","prompt": "介绍一下湖南省常德市","temperature": 0.0,"max_tokens": 512}'
curl -X POST http://0.0.0.0:1234/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{"model": "/home/Qwen/Qwen3-8B/","prompt": "介绍一下湖南省常德市","temperature": 0.0,"max_tokens": 512}'
curl -X POST http://0.0.0.0:1234/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{"model": "/home/Qwen/Qwen3-14B/","prompt": "介绍一下湖南省常德市","temperature": 0.0,"max_tokens": 512}'
curl -X POST http://0.0.0.0:1234/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{"model": "/home/Qwen/Qwen3-32B/","prompt": "介绍一下湖南省常德市","temperature": 0.0,"max_tokens": 512}'
1、返回值乱码问题,尝试修改模型精度,增加下面的参数
--dtype float16
或者
--dtype bfloat16