Sign inSign up

roboflow/roboflow-inference-server-gpu-slim:1.1.2

Index digest

sha256:5b845d9409ecf84be27a03b67433f7c6ad9b83d001090291c43bd216f41941ca

OS/ARCH

linux/amd64

Compressed size

7.73 GB

Last pushed

4 months by roboflowpaul

Type

Image

Manifest digest

sha256:4248d7648a528b96cf5d6da1d8cd597fd514d0e548647f3d9fcc59317ad6faa8

Image Layers

Image Layers

1COPY / / # buildkit7.72 GB
2WORKDIR /app/34 B
3COPY inference inference # buildkit4.94 MB
4COPY inference_sdk inference_sdk # buildkit50.01 KB
5COPY inference_cli inference_cli # buildkit69.58 KB
6ENV PYTHONPATH=/app/0 B
7COPY docker/config/gpu_http.py gpu_http.py # buildkit743 B
8ENV CORE_MODEL_CLIP_ENABLED=false0 B
9ENV CORE_MODEL_PE_ENABLED=false0 B
10ENV CORE_MODEL_SAM_ENABLED=false0 B
11ENV CORE_MODEL_GAZE_ENABLED=false0 B
12ENV CORE_MODEL_DOCTR_ENABLED=false0 B
13ENV VERSION_CHECK_MODE=continuous0 B
14ENV PROJECT=roboflow-platform0 B
15ENV NUM_WORKERS=10 B
16ENV HOST=0.0.0.00 B
17ENV PORT=90010 B
18ENV WORKFLOWS_STEP_EXECUTION_MODE=local0 B
19ENV WORKFLOWS_MAX_CONCURRENT_STEPS=40 B
20ENV API_LOGGING_ENABLED=True0 B
21ENV CORE_MODEL_TROCR_ENABLED=false0 B
22ENV ENABLE_PROMETHEUS=True0 B
23ENV CORE_MODEL_EASYOCR_ENABLED=False0 B
24ENV CORE_MODEL_SAM3_ENABLED=False0 B
25ENTRYPOINT ["/bin/sh" "-c" "uvicorn gpu_http:app0 B

Command

COPY / / # buildkit