Container Compute Service:inference-nv-pytorch 25.07

What's new

Image specifications

This release provides two image variants, both targeting Large Language Model (LLM) inference on PyTorch with CUDA 12.8.

Image access

acs-registry-vpc.{region-id}.cr.aliyuncs.com/egslingjun/{image:tag}

Driver requirement

CUDA 12.8 images require NVIDIA Driver 570 or later.

Quick start

This example pulls the vLLM image, downloads the Qwen2.5-7B-Instruct model, and runs an inference test.

1. Pull the image.

   docker pull egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:[tag]

2. Download the model from ModelScope.

   pip install modelscope
   cd /mnt
   modelscope download --model Qwen/Qwen2.5-7B-Instruct --local_dir ./Qwen2.5-7B-Instruct

3. Launch the container.

   docker run -d -t --network=host --privileged --init --ipc=host \
     --ulimit memlock=-1 --ulimit stack=67108864 \
     -v /mnt/:/mnt/ \
     egslingjun-registry.cn-wulanchabu.cr.aliyuncs.com/egslingjun/inference-nv-pytorch:[tag]

4. Start the vLLM inference server.

   python3 -m vllm.entrypoints.openai.api_server \
     --model /mnt/Qwen2.5-7B-Instruct \
     --trust-remote-code --disable-custom-all-reduce \
     --tensor-parallel-size 1

5. Send a test request from the client.

   curl http://localhost:8000/v1/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
       "model": "/mnt/Qwen2.5-7B-Instruct",
       "messages": [
         {"role": "system", "content": "You are a friendly AI assistant."},
         {"role": "user", "content": "Please introduce deep learning."}
       ]
     }'

   For more information, see the vLLM documentation.

Known issues

The deepgpu-comfyui plugin for Wanx model video generation supports only gn8is instance types.