# blink server image: this repository's weights and runtime; Hugging Face libraries run in offline mode.
#   hf download thegovind/<model> --revision <sha> --local-dir blink && cd blink
#   docker build -t blink . && docker run --rm --gpus all -p 127.0.0.1:8000:8000 blink
#   curl -s http://127.0.0.1:8000/healthz     # weights_verified, warmup.repeat_identical, kernels
FROM pytorch/pytorch:2.13.0-cuda12.6-cudnn9-runtime
ENV PIP_BREAK_SYSTEM_PACKAGES=1 PIP_NO_CACHE_DIR=1 PIP_DISABLE_PIP_VERSION_CHECK=1
RUN pip install "transformers==5.17.0" "torchvision==0.28.0" "flash-linear-attention==0.5.2" "accelerate>=1.0" "safetensors>=0.4" "huggingface_hub>=1.0"
COPY . /blink
ENV HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 HF_HUB_DISABLE_TELEMETRY=1
EXPOSE 8000
CMD ["python", "/blink/serve.py", "--model", "/blink", "--host", "0.0.0.0", "--port", "8000"]