Skip to content

Commit

Permalink
ci: docker 1.16.1 release (#38)
Browse files Browse the repository at this point in the history
  • Loading branch information
kibae authored Oct 13, 2023
1 parent d07a642 commit 505a731
Show file tree
Hide file tree
Showing 9 changed files with 26 additions and 17 deletions.
10 changes: 5 additions & 5 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@

- [ONNX Runtime](https://onnxruntime.ai/)
- [Boost](https://www.boost.org/)
- [CMake](https://cmake.org/)
- [CMake](https://cmake.org/), pkg-config
- CUDA(*optional, for Nvidia GPU support*)
- OpenSSL(*optional, for HTTPS*)

Expand Down Expand Up @@ -66,7 +66,7 @@ brew install onnxruntime
#### Ubuntu/Debian

```shell
sudo apt install cmake libboost-all-dev libssl-dev
sudo apt install cmake pkg-config libboost-all-dev libssl-dev
# optional, for Nvidia GPU support
sudo apt install nvidia-cuda-toolkit nvidia-cudnn
# optional, for Nvidia GPU support with Docker
Expand Down Expand Up @@ -147,13 +147,13 @@ sudo cmake --install build --prefix /usr/local/onnxruntime-server
# Docker

- Docker hub: [kibaes/onnxruntime-server](https://hub.docker.com/r/kibaes/onnxruntime-server)
- [`1.2.1-linux-cuda`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cuda.dockerfile)
- [`1.16.1-linux-cuda`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cuda.dockerfile)
amd64
- [`1.2.1-linux-cpu`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cpu.dockerfile)
- [`1.16.1-linux-cpu`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cpu.dockerfile)
amd64, arm64

```shell
DOCKER_IMAGE=kibae/onnxruntime-server:1.2.1-linux-cuda # or kibae/onnxruntime-server:1.2.1-linux-cpu
DOCKER_IMAGE=kibae/onnxruntime-server:1.16.1-linux-cuda # or kibae/onnxruntime-server:1.16.1-linux-cpu

docker pull ${DOCKER_IMAGE}

Expand Down
2 changes: 1 addition & 1 deletion deploy/build-docker/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

## x64 with CUDA

- [ONNX Runtime Binary](https://github.com/microsoft/onnxruntime/releases) v1.15.1(latest) requires CUDA 11, cudnn 8.
- [ONNX Runtime Binary](https://github.com/microsoft/onnxruntime/releases) v1.16.1(latest) requires CUDA 11, cudnn 8.
```
$ ldd libonnxruntime_providers_cuda.so
linux-vdso.so.1 (0x00007fffa4bf8000)
Expand Down
2 changes: 1 addition & 1 deletion deploy/build-docker/VERSION
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
export VERSION=1.2.1
export VERSION=1.16.1
export IMAGE_PREFIX=kibaes/onnxruntime-server
4 changes: 2 additions & 2 deletions deploy/build-docker/docker-compose.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ services:
onnxruntime_server_simple:
# After the docker container is up, you can use the REST API (http://localhost:8080).
# API documentation will be available at http://localhost:8080/api-docs.
image: kibaes/onnxruntime-server:1.2.1-linux-cuda
image: kibaes/onnxruntime-server:1.16.1-linux-cuda
ports:
- "8080:80" # for http backend
volumes:
Expand All @@ -29,7 +29,7 @@ services:
onnxruntime_server_advanced:
# After the docker container is up, you can use the REST API (http://localhost, https://localhost).
# API documentation will be available at http://localhost/api-docs.
image: kibaes/onnxruntime-server:1.2.1-linux-cuda
image: kibaes/onnxruntime-server:1.16.1-linux-cuda
ports:
- "80:80" # for http backend
- "443:443" # for https backend
Expand Down
9 changes: 9 additions & 0 deletions deploy/build-docker/docker-image-test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,15 @@ else
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{"model": "sample", "version": "2"}' | jq || exit 1

ERROR=$(curl -sX 'GET' \
'http://localhost:8080/api/sessions/sample/2' \
-H 'accept: application/json' | jq '.error' || exit 1)

if [ "${ERROR}" != "null" ]; then
echo ${ERROR}
exit 1
fi
fi

curl -sX 'POST' \
Expand Down
2 changes: 1 addition & 1 deletion deploy/build-docker/linux-cpu.dockerfile
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
FROM ubuntu:latest AS builder

RUN apt update && apt install -y curl wget git build-essential cmake libboost-all-dev libssl-dev
RUN apt update && apt install -y curl wget git build-essential cmake pkg-config libboost-all-dev libssl-dev
RUN mkdir -p /app/source

WORKDIR /app/source
Expand Down
2 changes: 1 addition & 1 deletion deploy/build-docker/linux-cuda.dockerfile
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04 AS builder

RUN apt update && apt install -y curl wget git build-essential cmake libboost-all-dev libssl-dev
RUN apt update && apt install -y curl wget git build-essential cmake pkg-config libboost-all-dev libssl-dev
RUN mkdir -p /app/source

WORKDIR /app/source
Expand Down
10 changes: 5 additions & 5 deletions docs/docker.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@

# Supported tags and respective Dockerfile links

- [`1.2.1-linux-cuda`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cuda.dockerfile)
- [`1.16.1-linux-cuda`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cuda.dockerfile)
amd64
- [`1.2.1-linux-cpu`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cpu.dockerfile)
- [`1.16.1-linux-cpu`](https://github.com/kibae/onnxruntime-server/blob/main/deploy/build-docker/linux-cpu.dockerfile)
amd64, arm64

# How to use this image
Expand All @@ -30,7 +30,7 @@
- API documentation will be available at http://localhost/api-docs.

```shell
DOCKER_IMAGE=kibae/onnxruntime-server:1.2.1-linux-cuda # or kibae/onnxruntime-server:1.2.1-linux-cpu
DOCKER_IMAGE=kibae/onnxruntime-server:1.16.1-linux-cuda # or kibae/onnxruntime-server:1.16.1-linux-cpu

docker pull ${DOCKER_IMAGE}

Expand Down Expand Up @@ -71,7 +71,7 @@ services:
onnxruntime_server_simple:
# After the docker container is up, you can use the REST API (http://localhost:8080).
# API documentation will be available at http://localhost:8080/api-docs.
image: kibaes/onnxruntime-server:1.2.1-linux-cuda
image: kibaes/onnxruntime-server:1.16.1-linux-cuda
ports:
- "8080:80" # for http backend
volumes:
Expand Down Expand Up @@ -103,7 +103,7 @@ services:
onnxruntime_server_advanced:
# After the docker container is up, you can use the REST API (http://localhost, https://localhost).
# API documentation will be available at http://localhost/api-docs.
image: kibaes/onnxruntime-server:1.2.1-linux-cuda
image: kibaes/onnxruntime-server:1.16.1-linux-cuda
ports:
- "80:80" # for http backend
- "443:443" # for https backend
Expand Down
2 changes: 1 addition & 1 deletion docs/swagger/openapi.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ openapi: 3.0.3
info:
title: ONNX Runtime Server
description: |-
version: 1.2.1
version: 1.16.1
externalDocs:
description: ONNX Runtime Server
url: https://github.com/kibae/onnxruntime-server
Expand Down

0 comments on commit 505a731

Please sign in to comment.