zishuo/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2025-09-26 11:31:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove TensorRT Detector from AMD64 Build (#19030)

Browse Source 
* Don't support tensorrt detector for amd64 builds

* Add logs for directing users not to use tensorrt detector

* Rework docs

* Fix dockerfile index

* Don't undo jetson fix
This commit is contained in:
Nicolas Mowen
2025-07-07 17:12:52 -06:00
committed by GitHub
parent fc608b31d7
commit d69916694b
9 changed files with 201 additions and 206 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
docker/tensorrt/Dockerfile.amd64
View File

@@ -6,24 +6,29 @@ ARG DEBIAN_FRONTEND=noninteractive
# Globally set pip break-system-packages option to avoid having to specify it every time
ARG PIP_BREAK_SYSTEM_PACKAGES=1
FROM tensorrt-base AS frigate-tensorrt
FROM wheels AS trt-wheels
ARG PIP_BREAK_SYSTEM_PACKAGES
ENV TRT_VER=8.6.1
# Install TensorRT wheels
COPY docker/tensorrt/requirements-amd64.txt /requirements-tensorrt.txt
RUN pip3 install -U -r /requirements-tensorrt.txt && ldconfig
COPY docker/main/requirements-wheels.txt /requirements-wheels.txt
RUN pip3 wheel --wheel-dir=/trt-wheels -c /requirements-wheels.txt -r /requirements-tensorrt.txt
FROM deps AS frigate-tensorrt
ARG PIP_BREAK_SYSTEM_PACKAGES
RUN --mount=type=bind,from=trt-wheels,source=/trt-wheels,target=/deps/trt-wheels \
pip3 uninstall -y onnxruntime-openvino tensorflow-cpu \
&& pip3 install -U /deps/trt-wheels/*.whl
COPY --from=rootfs / /
COPY docker/tensorrt/detector/rootfs/etc/ld.so.conf.d /etc/ld.so.conf.d
RUN ldconfig
WORKDIR /opt/frigate/
COPY --from=rootfs / /
# Dev Container w/ TRT
FROM devcontainer AS devcontainer-trt
COPY --from=trt-deps /usr/local/lib/libyolo_layer.so /usr/local/lib/libyolo_layer.so
COPY --from=trt-deps /usr/local/src/tensorrt_demos /usr/local/src/tensorrt_demos
COPY --from=trt-deps /usr/local/cuda-12.1 /usr/local/cuda
COPY docker/tensorrt/detector/rootfs/ /
COPY --from=trt-deps /usr/local/lib/libyolo_layer.so /usr/local/lib/libyolo_layer.so
RUN --mount=type=bind,from=trt-wheels,source=/trt-wheels,target=/deps/trt-wheels \
pip3 install -U /deps/trt-wheels/*.whl

58
docker/tensorrt/Dockerfile.arm64
View File

@@ -1,9 +1,61 @@
# syntax=docker/dockerfile:1.4
# syntax=docker/dockerfile:1.6
# https://askubuntu.com/questions/972516/debian-frontend-environment-variable
ARG DEBIAN_FRONTEND=noninteractive
ARG BASE_IMAGE
ARG TRT_BASE=nvcr.io/nvidia/tensorrt:23.12-py3
# Build TensorRT-specific library
FROM ${TRT_BASE} AS trt-deps
ARG TARGETARCH
ARG COMPUTE_LEVEL
RUN apt-get update \
&& apt-get install -y git build-essential cuda-nvcc-* cuda-nvtx-* libnvinfer-dev libnvinfer-plugin-dev libnvparsers-dev libnvonnxparsers-dev \
&& rm -rf /var/lib/apt/lists/*
RUN --mount=type=bind,source=docker/tensorrt/detector/tensorrt_libyolo.sh,target=/tensorrt_libyolo.sh \
/tensorrt_libyolo.sh
# COPY required individual CUDA deps
RUN mkdir -p /usr/local/cuda-deps
RUN if [ "$TARGETARCH" = "amd64" ]; then \
cp /usr/local/cuda-12.3/targets/x86_64-linux/lib/libcurand.so.* /usr/local/cuda-deps/ && \
cp /usr/local/cuda-12.3/targets/x86_64-linux/lib/libnvrtc.so.* /usr/local/cuda-deps/ && \
cd /usr/local/cuda-deps/ && \
for lib in libnvrtc.so.*; do \
if [[ "$lib" =~ libnvrtc.so\.([0-9]+\.[0-9]+\.[0-9]+) ]]; then \
version="${BASH_REMATCH[1]}"; \
ln -sf "libnvrtc.so.$version" libnvrtc.so; \
fi; \
done && \
for lib in libcurand.so.*; do \
if [[ "$lib" =~ libcurand.so\.([0-9]+\.[0-9]+\.[0-9]+\.[0-9]+) ]]; then \
version="${BASH_REMATCH[1]}"; \
ln -sf "libcurand.so.$version" libcurand.so; \
fi; \
done; \
fi
# Frigate w/ TensorRT Support as separate image
FROM deps AS tensorrt-base
#Disable S6 Global timeout
ENV S6_CMD_WAIT_FOR_SERVICES_MAXTIME=0
# COPY TensorRT Model Generation Deps
COPY --from=trt-deps /usr/local/lib/libyolo_layer.so /usr/local/lib/libyolo_layer.so
COPY --from=trt-deps /usr/local/src/tensorrt_demos /usr/local/src/tensorrt_demos
# COPY Individual CUDA deps folder
COPY --from=trt-deps /usr/local/cuda-deps /usr/local/cuda
COPY docker/tensorrt/detector/rootfs/ /
ENV YOLO_MODELS=""
HEALTHCHECK --start-period=600s --start-interval=5s --interval=15s --timeout=5s --retries=3 \
CMD curl --fail --silent --show-error http://127.0.0.1:5000/api/version || exit 1
FROM ${BASE_IMAGE} AS build-wheels
ARG DEBIAN_FRONTEND
@@ -100,4 +152,4 @@ WORKDIR /opt/frigate/
COPY --from=rootfs / /
# Fixes "Error importing detector runtime: /usr/lib/aarch64-linux-gnu/libstdc++.so.6: cannot allocate memory in static TLS block"
ENV LD_PRELOAD /usr/lib/aarch64-linux-gnu/libstdc++.so.6
ENV LD_PRELOAD /usr/lib/aarch64-linux-gnu/libstdc++.so.6

57
docker/tensorrt/Dockerfile.base
View File

@@ -1,57 +0,0 @@
# syntax=docker/dockerfile:1.6
# https://askubuntu.com/questions/972516/debian-frontend-environment-variable
ARG DEBIAN_FRONTEND=noninteractive
ARG TRT_BASE=nvcr.io/nvidia/tensorrt:23.12-py3
# Build TensorRT-specific library
FROM ${TRT_BASE} AS trt-deps
ARG TARGETARCH
ARG COMPUTE_LEVEL
RUN apt-get update \
&& apt-get install -y git build-essential cuda-nvcc-* cuda-nvtx-* libnvinfer-dev libnvinfer-plugin-dev libnvparsers-dev libnvonnxparsers-dev \
&& rm -rf /var/lib/apt/lists/*
RUN --mount=type=bind,source=docker/tensorrt/detector/tensorrt_libyolo.sh,target=/tensorrt_libyolo.sh \
/tensorrt_libyolo.sh
# COPY required individual CUDA deps
RUN mkdir -p /usr/local/cuda-deps
RUN if [ "$TARGETARCH" = "amd64" ]; then \
cp /usr/local/cuda-12.3/targets/x86_64-linux/lib/libcurand.so.* /usr/local/cuda-deps/ && \
cp /usr/local/cuda-12.3/targets/x86_64-linux/lib/libnvrtc.so.* /usr/local/cuda-deps/ && \
cd /usr/local/cuda-deps/ && \
for lib in libnvrtc.so.*; do \
if [[ "$lib" =~ libnvrtc.so\.([0-9]+\.[0-9]+\.[0-9]+) ]]; then \
version="${BASH_REMATCH[1]}"; \
ln -sf "libnvrtc.so.$version" libnvrtc.so; \
fi; \
done && \
for lib in libcurand.so.*; do \
if [[ "$lib" =~ libcurand.so\.([0-9]+\.[0-9]+\.[0-9]+\.[0-9]+) ]]; then \
version="${BASH_REMATCH[1]}"; \
ln -sf "libcurand.so.$version" libcurand.so; \
fi; \
done; \
fi
# Frigate w/ TensorRT Support as separate image
FROM deps AS tensorrt-base
#Disable S6 Global timeout
ENV S6_CMD_WAIT_FOR_SERVICES_MAXTIME=0
# COPY TensorRT Model Generation Deps
COPY --from=trt-deps /usr/local/lib/libyolo_layer.so /usr/local/lib/libyolo_layer.so
COPY --from=trt-deps /usr/local/src/tensorrt_demos /usr/local/src/tensorrt_demos
# COPY Individual CUDA deps folder
COPY --from=trt-deps /usr/local/cuda-deps /usr/local/cuda
COPY docker/tensorrt/detector/rootfs/ /
ENV YOLO_MODELS=""
HEALTHCHECK --start-period=600s --start-interval=5s --interval=15s --timeout=5s --retries=3 \
CMD curl --fail --silent --show-error http://127.0.0.1:5000/api/version || exit 1

7
docker/tensorrt/detector/rootfs/etc/ld.so.conf.d/cuda_tensorrt.conf
View File

@@ -1,7 +1,6 @@
/usr/local/lib
/usr/local/cuda
/usr/local/lib/python3.11/dist-packages/tensorrt
/usr/local/lib/python3.11/dist-packages/nvidia/cudnn/lib
/usr/local/lib/python3.11/dist-packages/nvidia/cuda_runtime/lib
/usr/local/lib/python3.11/dist-packages/nvidia/cublas/lib
/usr/local/lib/python3.11/dist-packages/nvidia/cufft/lib
/usr/local/lib/python3.11/dist-packages/nvidia/cufft/lib
/usr/local/lib/python3.11/dist-packages/nvidia/curand/lib/
/usr/local/lib/python3.11/dist-packages/nvidia/cuda_nvrtc/lib/

27
docker/tensorrt/requirements-amd64.txt
View File

@@ -1,17 +1,18 @@
# NVidia TensorRT Support (amd64 only)
--extra-index-url 'https://pypi.nvidia.com'
numpy < 1.24; platform_machine == 'x86_64'
tensorrt == 8.6.1; platform_machine == 'x86_64'
tensorrt_bindings == 8.6.1; platform_machine == 'x86_64'
cuda-python == 11.8.*; platform_machine == 'x86_64'
cython == 3.0.*; platform_machine == 'x86_64'
nvidia-cuda-runtime-cu12 == 12.1.*; platform_machine == 'x86_64'
nvidia-cuda-runtime-cu11 == 11.8.*; platform_machine == 'x86_64'
nvidia-cublas-cu11 == 11.11.3.6; platform_machine == 'x86_64'
nvidia-cudnn-cu11 == 8.6.0.*; platform_machine == 'x86_64'
nvidia-cudnn-cu12 == 9.5.0.*; platform_machine == 'x86_64'
nvidia-cufft-cu11==10.*; platform_machine == 'x86_64'
nvidia-cufft-cu12==11.*; platform_machine == 'x86_64'
cython==3.0.*; platform_machine == 'x86_64'
nvidia_cuda_cupti_cu12==12.5.82; platform_machine == 'x86_64'
nvidia-cublas-cu12==12.5.3.*; platform_machine == 'x86_64'
nvidia-cudnn-cu12==9.3.0.*; platform_machine == 'x86_64'
nvidia-cufft-cu12==11.2.3.*; platform_machine == 'x86_64'
nvidia-curand-cu12==10.3.6.*; platform_machine == 'x86_64'
nvidia_cuda_nvcc_cu12==12.5.82; platform_machine == 'x86_64'
nvidia-cuda-nvrtc-cu12==12.5.82; platform_machine == 'x86_64'
nvidia_cuda_runtime_cu12==12.5.82; platform_machine == 'x86_64'
nvidia_cusolver_cu12==11.6.3.*; platform_machine == 'x86_64'
nvidia_cusparse_cu12==12.5.1.*; platform_machine == 'x86_64'
nvidia_nccl_cu12==2.23.4; platform_machine == 'x86_64'
nvidia_nvjitlink_cu12==12.5.82; platform_machine == 'x86_64'
onnx==1.16.*; platform_machine == 'x86_64'
onnxruntime-gpu==1.20.*; platform_machine == 'x86_64'
onnxruntime-gpu==1.22.*; platform_machine == 'x86_64'
protobuf==3.20.3; platform_machine == 'x86_64'

12
docker/tensorrt/trt.hcl
View File

@@ -79,21 +79,13 @@ target "trt-deps" {
inherits = ["_build_args"]
}
target "tensorrt-base" {
dockerfile = "docker/tensorrt/Dockerfile.base"
context = "."
contexts = {
deps = "target:deps",
}
inherits = ["_build_args"]
}
target "tensorrt" {
dockerfile = "docker/tensorrt/Dockerfile.${ARCH}"
context = "."
contexts = {
wget = "target:wget",
tensorrt-base = "target:tensorrt-base",
wheels = "target:wheels",
deps = "target:deps",
rootfs = "target:rootfs"
}
target = "frigate-tensorrt"