Spaces:
Paused
Paused
Download Dockerfile from dev2nd/quiz-llm-server: direct link, hf CLI and curl.
- Browser
- Download file 761 Bytes
-
https://huggingface.co/spaces/dev2nd/quiz-llm-server/resolve/main/Dockerfile
- Command line
-
hf download hf://spaces/dev2nd/quiz-llm-server/Dockerfile
-
curl -L -o Dockerfile https://huggingface.co/spaces/dev2nd/quiz-llm-server/resolve/main/Dockerfile
761 Bytes
| FROM vllm/vllm-openai:latest | |
| ENV PORT=7860 | |
| ENV HF_HOME=/tmp/hf_home | |
| ENV HUGGINGFACE_HUB_CACHE=/tmp/hf_home/hub | |
| ENV TRANSFORMERS_CACHE=/tmp/hf_home/transformers | |
| # HF Spaces๊ฐ UID 1000์ผ๋ก ์คํํ๋ vllm ์ด๋ฏธ์ง์ ํด๋น ์ฌ์ฉ์๊ฐ ์์ด | |
| # getpass.getuser()๊ฐ ์คํจํจ. ์๋ ํ๊ฒฝ๋ณ์๋ค์ด ๊ทธ ์ฐํ๋ก์. | |
| ENV USER=user | |
| ENV HOME=/tmp | |
| ENV TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor | |
| ENV TRITON_CACHE_DIR=/tmp/triton | |
| ENV XDG_CACHE_HOME=/tmp/.cache | |
| EXPOSE 7860 | |
| ENTRYPOINT ["sh", "-c", "python3 -m vllm.entrypoints.openai.api_server \ | |
| --model ${MODEL_ID:-Qwen/Qwen2.5-7B-Instruct} \ | |
| --host 0.0.0.0 \ | |
| --port 7860 \ | |
| --max-model-len ${MAX_MODEL_LEN:-8192} \ | |
| --gpu-memory-utilization ${GPU_MEM_UTIL:-0.90} \ | |
| --dtype auto"] |