| FROM vllm/vllm-openai:latest | |
| WORKDIR /app | |
| EXPOSE 7860 | |
| CMD exec vllm serve --model Qwen/Qwen3-0.6B \ | |
| --host 0.0.0.0 \ | |
| --port 7860 \ | |
| --max-model-len 8192 \ | |
| --dtype float32 \ | |
| --enable-reasoning \ | |
| --reasoning-parser deepseek_r1 \ | |
| --engine-use-ray \ | |
| --trust-remote-code \ | |
| --disable-log-requests | |