File size: 841 Bytes
3ea2a7d
cb96e5d
 
 
 
 
10ca145
 
572dc0d
46485d7
2b10985
3ea2a7d
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
#!/bin/bash
sudo apt-get update -y
sudo apt-get install -y gcc-12 g++-12
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
pip install -v -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu

git clone https://github.com/vllm-project/vllm.git
cd vllm && VLLM_TARGET_DEVICE=cpu python setup.py install && cd ..
git clone https://huggingface.co/Moses25/Mistral-7B-Instruct-32K-AWQ

eexport VLLM_CPU_KVCACHE_SPACE=15
python  -m vllm.entrypoints.openai.api_server --model=Mistral-7B-Instruct-32K-AWQ \
        --trust-remote-code --host 0.0.0.0  --port 7777 \
        --gpu-memory-utilization 0.8 \
        --enforce-eager \
        --max-model-len 8192 --chat-template llama2-chat-template.jinja \
        --tensor-parallel-size 1 --served-model-name dewu-chat