From 35e623f114334a7a5ec52b7160071bdf76849545 Mon Sep 17 00:00:00 2001 From: Sachin Agarwal Date: Wed, 19 Feb 2025 22:24:15 +0000 Subject: [PATCH 1/3] Fix the multistage build --- docker/dockerfiles/Dockerfile.onnx.gpu | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/docker/dockerfiles/Dockerfile.onnx.gpu b/docker/dockerfiles/Dockerfile.onnx.gpu index b9a220bda8..9147111118 100644 --- a/docker/dockerfiles/Dockerfile.onnx.gpu +++ b/docker/dockerfiles/Dockerfile.onnx.gpu @@ -1,4 +1,4 @@ -FROM nvcr.io/nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04 as base +FROM nvcr.io/nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04 as builder WORKDIR /app @@ -49,13 +49,30 @@ RUN python3 -m pip install \ && rm -rf ~/.cache/pip # Install setup.py requirements for flash_attn -RUN python3 -m pip install packaging==24.1 && rm -rf ~/.cache/pip +RUN python3 -m pip install packaging==24.1 && rm -rf ~/.cache/pip # Install flash_attn required for Paligemma and Florence2 RUN python3 -m pip install -r requirements.pali.flash_attn.txt --no-build-isolation && rm -rf ~/.cache/pip -FROM scratch -COPY --from=base / / +# Start runtime stage +FROM nvcr.io/nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04 as runtime + +WORKDIR /app + +# Copy Python and installed packages from builder +COPY --from=builder /usr/local/lib/python3.10 /usr/local/lib/python3.10 +COPY --from=builder /usr/local/bin /usr/local/bin + +# Install runtime dependencies +RUN rm -rf /var/lib/apt/lists/* && apt-get clean && apt-get update -y && DEBIAN_FRONTEND=noninteractive apt-get install -y \ + libxext6 \ + libopencv-dev \ + uvicorn \ + python3-pip \ + git \ + libgdal-dev \ + wget \ + && rm -rf /var/lib/apt/lists/* WORKDIR /build COPY . . From f5b815082dde70d587cfd6045c3076dc591a7389 Mon Sep 17 00:00:00 2001 From: Grzegorz Klimaszewski <166530809+grzegorz-roboflow@users.noreply.github.com> Date: Fri, 21 Feb 2025 10:54:30 +0100 Subject: [PATCH 2/3] Add rustc and cargo --- docker/dockerfiles/Dockerfile.onnx.gpu | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docker/dockerfiles/Dockerfile.onnx.gpu b/docker/dockerfiles/Dockerfile.onnx.gpu index 16bfcb5445..600f37da7c 100644 --- a/docker/dockerfiles/Dockerfile.onnx.gpu +++ b/docker/dockerfiles/Dockerfile.onnx.gpu @@ -72,6 +72,8 @@ RUN rm -rf /var/lib/apt/lists/* && apt-get clean && apt-get update -y && DEBIAN_ git \ libgdal-dev \ wget \ + rustc \ + cargo \ && rm -rf /var/lib/apt/lists/* WORKDIR /build @@ -103,4 +105,4 @@ ENV ENABLE_WORKFLOWS_PROFILING=True ENV ENABLE_PROMETHEUS=True ENV STREAM_API_PRELOADED_PROCESSES=2 -ENTRYPOINT uvicorn gpu_http:app --workers $NUM_WORKERS --host $HOST --port $PORT \ No newline at end of file +ENTRYPOINT uvicorn gpu_http:app --workers $NUM_WORKERS --host $HOST --port $PORT From 7991f363bf9b6877a77b3c6316df5070a51e18a3 Mon Sep 17 00:00:00 2001 From: Grzegorz Klimaszewski <166530809+grzegorz-roboflow@users.noreply.github.com> Date: Fri, 21 Feb 2025 10:55:34 +0100 Subject: [PATCH 3/3] 0.39.0 --- inference/core/version.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/inference/core/version.py b/inference/core/version.py index 2034582893..540a9a9c7e 100644 --- a/inference/core/version.py +++ b/inference/core/version.py @@ -1,4 +1,4 @@ -__version__ = "0.39.0rc2" +__version__ = "0.39.0" if __name__ == "__main__":