vLLM+Open-WebUI環境をdocker containerで作る - Qiita

services: vllm: image: vllm/vllm-openai:latest runtime: nvidia ipc: host shm_size: "4g" command: > --model=/models/Qwen3-4B-AWQ --tokenizer=Qwen/Qwen3-4B-AWQ --quantization=awq --dtype=float16 --tensor-parallel-size=2 --max-model-len=8192 --download-dir=/models --host=0.0.0.0 --port=8000 ports: ["8000:8000"] environment: - VLLM_USE_V1=0 - DISABLE_CUSTOM_ALL_REDUCE=1 - NVIDIA_VISIBLE_DEVICES=0,1 vo