Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Upgrade to onnxruntime 0.19 #753

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Upgrade to onnxruntime 0.19 #753

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ed6224c
Upgrade onnxruntime to 1.19
yeldarby Oct 17, 2024
1b90c6e
Make TRT container work with new onnxruntime
yeldarby Oct 17, 2024
35acba5
Pull up parallel GPU docker
yeldarby Oct 17, 2024
f466703
Update additional Dockerfiles
yeldarby Oct 18, 2024
c2f742c
Merge branch 'main' into onnxruntime-1-19
yeldarby Oct 18, 2024
295418d
Be more friendly with dependency constraint
yeldarby Oct 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion docker/dockerfiles/Dockerfile.onnx.gpu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,9 @@ COPY requirements/requirements.sam.txt \
./

RUN python3 -m pip install -U pip
RUN python3 -m pip install --extra-index-url https://download.pytorch.org/whl/cu118 \
RUN python3 -m pip install \
--extra-index-url https://download.pytorch.org/whl/cu118 \
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what is this guy doing? changing the default cuda version for onnxruntime? so onnxruntime installs cuda?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The default is now to install the onnxruntime that's compatible with CUDA 12; this forces it to install the one built for CUDA 11 instead. (It used to be the reverse; you had to choose the channel for CUDA 12 and the default was 11)

-r _requirements.txt \
-r requirements.sam.txt \
-r requirements.clip.txt \
Expand Down
4 changes: 3 additions & 1 deletion docker/dockerfiles/Dockerfile.onnx.gpu.dev
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,9 @@ COPY requirements/requirements.sam.txt \
./

RUN python3 -m pip install -U pip
RUN python3 -m pip install --extra-index-url https://download.pytorch.org/whl/cu118 \
RUN python3 -m pip install \
--extra-index-url https://download.pytorch.org/whl/cu118 \
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \
-r _requirements.txt \
-r requirements.sam.txt \
-r requirements.clip.txt \
Expand Down
4 changes: 3 additions & 1 deletion docker/dockerfiles/Dockerfile.onnx.gpu.parallel
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
FROM nvcr.io/nvidia/cuda:11.7.1-cudnn8-runtime-ubuntu22.04 as base
FROM nvcr.io/nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04 as base

WORKDIR /app

Expand All @@ -21,6 +21,8 @@ COPY requirements/requirements.sam.txt \
./

RUN pip3 install --upgrade pip && pip3 install \
--extra-index-url https://download.pytorch.org/whl/cu118 \
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \
-r _requirements.txt \
-r requirements.sam.txt \
-r requirements.clip.txt \
Expand Down
3 changes: 2 additions & 1 deletion docker/dockerfiles/Dockerfile.onnx.gpu.slim
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
FROM nvcr.io/nvidia/cuda:11.7.1-cudnn8-runtime-ubuntu22.04 as base
FROM nvcr.io/nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04 as base

WORKDIR /app

Expand All @@ -20,6 +20,7 @@ COPY requirements/requirements.http.txt \
./

RUN pip3 install --upgrade pip && pip3 install \
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \
-r _requirements.txt \
-r requirements.http.txt \
-r requirements.gpu.txt \
Expand Down
3 changes: 2 additions & 1 deletion docker/dockerfiles/Dockerfile.onnx.gpu.stream_manager
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
FROM nvcr.io/nvidia/cuda:11.4.2-cudnn8-runtime-ubuntu20.04
FROM nvcr.io/nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04

WORKDIR /app

Expand All @@ -17,6 +17,7 @@ COPY requirements/requirements.http.txt \
./

RUN pip3 install --upgrade pip && pip3 install \
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \
-r _requirements.txt \
-r requirements.http.txt \
-r requirements.gpu.txt \
Expand Down
6 changes: 3 additions & 3 deletions docker/dockerfiles/Dockerfile.onnx.jetson.5.1.1
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,10 +56,10 @@ RUN python3.9 -m pip install --upgrade pip && python3.9 -m pip install \
&& rm -rf ~/.cache/pip

RUN python3.9 -m pip uninstall --yes onnxruntime
RUN wget https://nvidia.box.com/shared/static/5dei4auhjh5ij7rmuvljmdy5q1en3bhf.whl -O onnxruntime_gpu-1.12.1-cp39-cp39-linux_aarch64.whl
RUN python3.9 -m pip install onnxruntime_gpu-1.12.1-cp39-cp39-linux_aarch64.whl "opencv-python-headless>4" \
RUN wget https://nvidia.box.com/shared/static/67zek28z497hs9aev7xg2c1wngdeyv4h.whl -O onnxruntime_gpu-1.16.0-cp39-cp39-linux_aarch64.whl
RUN python3.9 -m pip install onnxruntime_gpu-1.16.0-cp39-cp39-linux_aarch64.whl "opencv-python-headless>4" \
&& rm -rf ~/.cache/pip \
&& rm onnxruntime_gpu-1.12.1-cp39-cp39-linux_aarch64.whl
&& rm onnxruntime_gpu-1.16.0-cp39-cp39-linux_aarch64.whl

WORKDIR /app/
COPY inference inference
Expand Down
6 changes: 3 additions & 3 deletions docker/dockerfiles/Dockerfile.onnx.jetson.5.1.1.stream_manager
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,10 +44,10 @@ RUN pip3 install --upgrade pip && pip3 install \
&& rm -rf ~/.cache/pip

RUN pip3 uninstall --yes onnxruntime
RUN wget https://nvidia.box.com/shared/static/v59xkrnvederwewo2f1jtv6yurl92xso.whl -O onnxruntime_gpu-1.12.1-cp38-cp38-linux_aarch64.whl
RUN pip3 install onnxruntime_gpu-1.12.1-cp38-cp38-linux_aarch64.whl "opencv-python-headless<4.3" \
RUN wget https://nvidia.box.com/shared/static/iizg3ggrtdkqawkmebbfixo7sce6j365.whl -O onnxruntime_gpu-1.16.0-cp38-cp38-linux_aarch64.whl
RUN pip3 install onnxruntime_gpu-1.16.0-cp38-cp38-linux_aarch64.whl "opencv-python-headless<4.3" \
&& rm -rf ~/.cache/pip \
&& rm onnxruntime_gpu-1.12.1-cp38-cp38-linux_aarch64.whl
&& rm onnxruntime_gpu-1.16.0-cp38-cp38-linux_aarch64.whl

WORKDIR /app/
COPY inference inference
Expand Down
2 changes: 2 additions & 0 deletions docker/dockerfiles/Dockerfile.onnx.trt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,8 @@ COPY requirements/requirements.sam.txt \
./

RUN pip install --upgrade pip && pip install \
--extra-index-url https://download.pytorch.org/whl/cu118 \
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \
-r _requirements.txt \
-r requirements.sam.txt \
-r requirements.clip.txt \
Expand Down
4 changes: 3 additions & 1 deletion docker/dockerfiles/Dockerfile.onnx.udp.gpu
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
FROM nvcr.io/nvidia/cuda:11.4.2-cudnn8-runtime-ubuntu20.04
FROM nvcr.io/nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04

WORKDIR /app

Expand All @@ -18,6 +18,8 @@ COPY requirements/requirements.sam.txt \
./

RUN pip3 install --upgrade pip && pip3 install \
--extra-index-url https://download.pytorch.org/whl/cu118 \
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-11/pypi/simple/ \
-r _requirements.txt \
-r requirements.sam.txt \
-r requirements.clip.txt \
Expand Down
2 changes: 1 addition & 1 deletion inference/core/env.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -264,7 +264,7 @@

ONNXRUNTIME_EXECUTION_PROVIDERS = os.getenv(
"ONNXRUNTIME_EXECUTION_PROVIDERS",
"[CUDAExecutionProvider,OpenVINOExecutionProvider,CPUExecutionProvider]",
"[CUDAExecutionProvider,OpenVINOExecutionProvider,CoreMLExecutionProvider,CPUExecutionProvider]",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

now everyone not on a mac is gonna get stupid warnings about not having coremlexecution provider :)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeh I was thinking we should probably update this default to be what onnxruntime.get_available_providers() reports but was going to do that in a different PR.

)

# Port, default is 9001
Expand Down
2 changes: 1 addition & 1 deletion requirements/requirements.cpu.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
onnxruntime~=1.15.1
onnxruntime>=1.15.1,<1.20.0
GPUtil==1.4.0
2 changes: 1 addition & 1 deletion requirements/requirements.gpu.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
onnxruntime-gpu~=1.15.1
onnxruntime-gpu>=1.15.1,<1.20.0
2 changes: 1 addition & 1 deletion requirements/requirements.vino.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
onnxruntime-openvino~=1.15.0
onnxruntime-openvino>=1.15.0,<1.20.0
Loading