File size: 761 Bytes
99990a1
 
 
 
 
 
 
e3b5c91
 
 
 
 
 
 
 
99990a1
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
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 1000์œผ๋กœ ์‹คํ–‰ํ•˜๋‚˜ vllm ์ด๋ฏธ์ง€์— ํ•ด๋‹น ์‚ฌ์šฉ์ž๊ฐ€ ์—†์–ด
# getpass.getuser()๊ฐ€ ์‹คํŒจํ•จ. ์•„๋ž˜ ํ™˜๊ฒฝ๋ณ€์ˆ˜๋“ค์ด ๊ทธ ์šฐํšŒ๋กœ์ž„.
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"]