cuda for arm64

separate base image

fix name

make sure onnxruntime-gpu is installed

use cuda again

add targetarch to build stage

.github/workflows/docker.yml

@@ -105,7 +105,7 @@ jobs:
           - platforms: linux/amd64,linux/arm64
             device: cpu
 
-          - platforms: linux/amd64
+          - platforms: linux/amd64,linux/arm64
             device: cuda
             suffix: -cuda
 

machine-learning/Dockerfile

@@ -17,7 +17,7 @@ RUN mkdir /opt/armnn && \
 
 FROM builder-${DEVICE} AS builder
 
-ARG DEVICE
+ARG DEVICE TARGETARCH
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
     PIP_NO_CACHE_DIR=true \
@@ -32,7 +32,11 @@ RUN poetry config installer.max-workers 10 && \
 RUN python3 -m venv /opt/venv
 
 COPY poetry.lock pyproject.toml ./
-RUN poetry install --sync --no-interaction --no-ansi --no-root --with ${DEVICE} --without dev
+RUN if [ "$DEVICE" = "cuda" ] && [ "$TARGETARCH" = "arm64" ]; then \
+    # hack to work around poetry not setting the right filename for the wheel https://github.com/python-poetry/poetry/issues/4472
+    wget -q -O onnxruntime_gpu-1.18.0-cp311-cp311-manylinux_aarch64.whl https://nvidia.box.com/shared/static/fy55jvniujjbigr4gwkv8z1ma6ipgspg.whl; fi && \
+    poetry install --sync --no-interaction --no-ansi --no-root --with ${DEVICE} --without dev && \
+    if [ "$DEVICE" = "cuda" ] && [ "$TARGETARCH" = "arm64" ]; then rm onnxruntime_gpu-1.18.0-cp311-cp311-manylinux_aarch64.whl; fi
 
 FROM python:3.11-slim-bookworm@sha256:5148c0e4bbb64271bca1d3322360ebf4bfb7564507ae32dd639322e4952a6b16 AS prod-cpu
 
@@ -49,13 +53,21 @@ RUN apt-get update && \
     apt-get remove wget -yqq && \
     rm -rf /var/lib/apt/lists/*
 
-FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04@sha256:94c1577b2cd9dd6c0312dc04dff9cb2fdce2b268018abc3d7c2dbcacf1155000 AS prod-cuda
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04@sha256:94c1577b2cd9dd6c0312dc04dff9cb2fdce2b268018abc3d7c2dbcacf1155000 AS prod-cuda-amd64
-
 RUN apt-get update && \
     apt-get install --no-install-recommends -yqq libcudnn9-cuda-12 && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04@sha256:94c1577b2cd9dd6c0312dc04dff9cb2fdce2b268018abc3d7c2dbcacf1155000 AS prod-cuda-arm64
+RUN apt-get update && \
+    apt-get install --no-install-recommends -yqq libcudnn8 && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+ENV LD_LIBRARY_PATH=/usr/local/cuda-12/compat:$LD_LIBRARY_PATH
+
+FROM prod-cuda-${TARGETARCH} AS prod-cuda
+
 COPY --from=builder-cuda /usr/local/bin/python3 /usr/local/bin/python3
 COPY --from=builder-cuda /usr/local/lib/python3.11 /usr/local/lib/python3.11
 COPY --from=builder-cuda /usr/local/lib/libpython3.11.so /usr/local/lib/libpython3.11.so
@@ -81,10 +93,10 @@ COPY --from=builder-armnn \
     /opt/armnn/
 
 FROM prod-${DEVICE} AS prod
-ARG DEVICE
+ARG DEVICE TARGETARCH
 
 RUN apt-get update && \
-    apt-get install -y --no-install-recommends tini $(if ! [ "$DEVICE" = "openvino" ]; then echo "libmimalloc2.0"; fi) && \
+    apt-get install -y --no-install-recommends tini $(if ! { [ "$DEVICE" = "openvino" ] || { [ "$DEVICE" = "cuda" ] && [ "$TARGETARCH" = "arm64" ]; }; }; then echo "libmimalloc2.0"; fi) && \
     apt-get autoremove -yqq && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*

machine-learning/poetry.lock

@@ -2090,6 +2090,28 @@ packaging = "*"
 protobuf = "*"
 sympy = "*"
 
+[[package]]
+name = "onnxruntime-gpu"
+version = "1.18.0"
+description = "ONNX Runtime is a runtime accelerator for Machine Learning models"
+optional = false
+python-versions = "*"
+files = [
+    {file = "onnxruntime_gpu-1.18.0-cp311-cp311-manylinux_aarch64.whl", hash = "sha256:7bdd6c373611235e43c8707fa528539327ff17a969448adf956ddf177d5fc8e7"},
+]
+
+[package.dependencies]
+coloredlogs = "*"
+flatbuffers = "*"
+numpy = ">=1.26.4"
+packaging = "*"
+protobuf = "*"
+sympy = "*"
+
+[package.source]
+type = "file"
+url = "onnxruntime_gpu-1.18.0-cp311-cp311-manylinux_aarch64.whl"
+
 [[package]]
 name = "onnxruntime-gpu"
 version = "1.19.2"
@@ -2806,7 +2828,6 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
     {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
     {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
     {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
@@ -3778,4 +3799,4 @@ testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<4.0"
-content-hash = "b690d5fbd141da3947f4f1dc029aba1b95e7faafd723166f2c4bdc47a66c095e"
+content-hash = "b2b053886ca1dd3a3305c63caf155b1976dfc4066f72f5d1ecfc42099db34aab"

machine-learning/pyproject.toml

@@ -45,7 +45,10 @@ onnxruntime = "^1.15.0"
 optional = true
 
 [tool.poetry.group.cuda.dependencies]
-onnxruntime-gpu = {version = "^1.17.0", source = "cuda12"}
+onnxruntime-gpu = [
+    { version = "^1.17.0", source = "cuda12", markers = "platform_machine == 'x86_64'" },
+    { python = "3.11", path = "onnxruntime_gpu-1.18.0-cp311-cp311-manylinux_aarch64.whl", markers = "platform_machine == 'aarch64'" }
+]
 
 [tool.poetry.group.openvino]
 optional = true

machine-learning/start.sh

@@ -1,19 +1,26 @@
 #!/usr/bin/env sh
 
-lib_path="/usr/lib/$(arch)-linux-gnu/libmimalloc.so.2"
 # mimalloc seems to increase memory usage dramatically with openvino, need to investigate
-if ! [ "$DEVICE" = "openvino" ]; then
+mimalloc="/usr/lib/$(arch)-linux-gnu/libmimalloc.so.2"
-	export LD_PRELOAD="$lib_path"
+if [ -f "$mimalloc" ]; then
-	export LD_BIND_NOW=1
+	export LD_PRELOAD="$mimalloc"
-	: "${MACHINE_LEARNING_WORKER_TIMEOUT:=120}"
-else
-	: "${MACHINE_LEARNING_WORKER_TIMEOUT:=300}"
 fi
 
+if { [ "$DEVICE" = "cuda" ] && [ "$(arch)" = "aarch64" ]; }; then
+	lib_path="/usr/lib/$(arch)-linux-gnu/libmimalloc.so.2"
+	export LD_PRELOAD="$lib_path"
+fi
+export LD_BIND_NOW=1
+
 : "${IMMICH_HOST:=[::]}"
 : "${IMMICH_PORT:=3003}"
 : "${MACHINE_LEARNING_WORKERS:=1}"
 : "${MACHINE_LEARNING_HTTP_KEEPALIVE_TIMEOUT_S:=2}"
+if [ "$DEVICE" = "openvino" ]; then
+	: "${MACHINE_LEARNING_WORKER_TIMEOUT:=300}"
+else
+	: "${MACHINE_LEARNING_WORKER_TIMEOUT:=120}"
+fi
 
 gunicorn app.main:app \
 	-k app.config.CustomUvicornWorker \