推理专属预置镜像列表
ModelArts的推理平台提供了一系列的基础镜像,用户可以基于这些基础镜像构建自定义镜像,用于部署推理服务。
X86架构(CPU/GPU)的推理基础镜像
AI引擎版本 |
支持的运行环境 |
镜像名称 |
URI |
---|---|---|---|
2.1.0 |
CPU GPU(cuda10.1) |
tensorflow_2.1.0-cuda_10.1-py_3.7-ubuntu_18.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/atelier/tensorflow_2_1:tensorflow_2.1.0-cuda_10.1-py_3.7-ubuntu_18.04-x86_64-20221121111529-d65d817 |
1.15.5 |
CPU GPU(cuda11.4) |
tensorflow_1.15.5-cuda_11.4-py_3.8-ubuntu_20.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/aip/tensorflow_1_15:tensorflow_1.15.5-cuda_11.4-py_3.8-ubuntu_20.04-x86_64-20220524162601-50d6a18 |
2.6.0 |
CPU GPU(cuda11.2) |
tensorflow_2.6.0-cuda_11.2-py_3.7-ubuntu_18.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/aip/tensorflow_2_6:tensorflow_2.6.0-cuda_11.2-py_3.7-ubuntu_18.04-x86_64-20220524162601-50d6a18 |
AI引擎版本 |
支持的运行环境 |
镜像名称 |
URI |
---|---|---|---|
1.8.0 |
CPU GPU(cuda10.2) |
pytorch_1.8.0-cuda_10.2-py_3.7-ubuntu_18.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/atelier/pytorch_1_8:pytorch_1.8.0-cuda_10.2-py_3.7-ubuntu_18.04-x86_64-20221118143845-d65d817 |
1.8.2 |
CPU GPU(cuda11.1) |
pytorch_1.8.2-cuda_11.1-py_3.7-ubuntu_18.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/aip/pytorch_1_8:pytorch_1.8.2-cuda_11.1-py_3.7-ubuntu_18.04-x86_64-20220524162601-50d6a18 |
AI引擎版本 |
支持的运行环境 |
镜像名称 |
URI |
---|---|---|---|
1.7.0 |
CPU |
mindspore_1.7.0-cpu-py_3.7-ubuntu_18.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/atelier/mindspore_1_7_0:mindspore_1.7.0-cpu-py_3.7-ubuntu_18.04-x86_64-20220702120711-8590b76 |
1.7.0 |
GPU(cuda10.1) |
mindspore_1.7.0-cuda_10.1-py_3.7-ubuntu_18.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/atelier/mindspore_1_7_0:mindspore_1.7.0-cuda_10.1-py_3.7-ubuntu_18.04-x86_64-20220702120711-8590b76 |
1.7.0 |
GPU(cuda11.1) |
mindspore_1.7.0-cuda_11.1-py_3.7-ubuntu_18.04-x86_64 |
swr.{region_id}.myhuaweicloud.com/atelier/mindspore_1_7_0:mindspore_1.7.0-cuda_11.1-py_3.7-ubuntu_18.04-x86_64-20220702120711-8590b76 |
ARM + Ascend架构的推理基础镜像
AI引擎版本 |
支持的运行环境 |
镜像名称 |
URI |
---|---|---|---|
1.15.0 |
Snt9 |
tensorflow_1.15-cann_5.1.0-py_3.7-euler_2.8.3-aarch64 |
swr.{region_id}.myhuaweicloud.com/atelier/tensorflow_1_15_ascend:tensorflow_1.15-cann_5.1.0-py_3.7-euler_2.8.3-aarch64-d910-20220715093657-9446c6a |
AI引擎版本 |
支持的运行环境 |
镜像名称 |
URI |
---|---|---|---|
1.8.1 |
Snt9 |
pytorch_1.8.1-cann_5.1.0-py_3.7-euler_2.8.3-aarch64 |
swr.{region_id}.myhuaweicloud.com/atelier/pytorch_1_8_ascend:pytorch_1.8.1-cann_5.1.0-py_3.7-euler_2.8.3-aarch64-d910-20220715093657-9446c6a |
AI引擎版本 |
支持的运行环境 |
镜像名称 |
URI |
---|---|---|---|
1.7.0 |
Snt9 |
mindspore_1.7.0-cann_5.1.0-py_3.7-euler_2.8.3-aarch64 |
swr.{region_id}.myhuaweicloud.com/atelier/mindspore_1_7_0:mindspore_1.7.0-cann_5.1.0-py_3.7-euler_2.8.3-aarch64-d910-20220715093657-9446c6a |
推理基础镜像详情TensorFlow(CPU/GPU)
ModelArts提供了以下TensorFlow(CPU/GPU)推理基础镜像:
推理基础镜像详情PyTorch(CPU/GPU)
ModelArts提供了以下PyTorch(CPU/GPU)推理基础镜像:
推理基础镜像详情MindSpore(CPU/GPU)
ModelArts提供了以下MindSpore(CPU/GPU)推理基础镜像:
推理基础镜像详情TensorFlow(Ascend)
ModelArts提供了以下TensorFlow(Ascend)推理基础镜像:
引擎版本一:tensorflow_1.15-cann_5.1.0-py_3.7-euler_2.8.3-aarch64
- 镜像地址:
swr.{region_id}.myhuaweicloud.com/atelier/tensorflow_1_15_ascend:tensorflow_1.15-cann_5.1.0-py_3.7-euler_2.8.3-aarch64-d910-20220715093657-9446c6a
- 镜像构建时间:20220715093657(yyyy-mm-dd-hh-mm-ss)
- 镜像系统版本:euleros 2.8.3
- cann:5.1.0
- Python解释器路径及版本:/home/ma-user/anaconda3/envs/TensorFlow-1.15.0/bin/python, python 3.7.10
- 三方包安装路径:/home/ma-user/anaconda3/envs/TensorFlow-1.15.0/lib/python3.7/site-packages
- 部分pip安装包列表:
Cython 0.29.14 Flask 2.0.1 grpcio 1.26.0 grpcio-tools 1.26.0 gunicorn 20.1.0 h5py 2.10.0 hccl 0.1.0 huaweicloud-sdk-python-modelarts-dataset 0.1.5 idna 2.10 image 1.5.28 imageio 2.9.0 ipykernel 6.7.0 Jinja2 3.0.1 Keras 2.3.1 matplotlib 3.5.1 mmcv 0.2.14 modelarts-mindspore-model-server 1.0.4 moxing-framework 2.0.1.rc0.ffd1c0c8 moxing-tensorflow 2.0.0.rc2.65f98f7d numpy 1.17.5 opencv-python 4.2.0.34 pandas 0.24.2 Pillow 9.2.0 pip 22.1.2 protobuf 3.11.3 psutil 5.7.0 ptyprocess 0.7.0 pycocotools 2.0.0 PyYAML 5.3.1 requests 2.27.1 scikit-image 0.17.2 scikit-learn 0.20.0 scipy 1.3.3 setuptools 63.1.0 tensorboard 1.15.0 tensorflow 1.15.0 tensorflow-estimator 1.15.1 tensorflow-probability 0.10.1 tqdm 4.46.1 wheel 0.37.1 zipp 3.8.1 ...
- 部分apt安装包列表:
ca-certificates.noarch cmake.aarch64 compat-openssl10.aarch64 curl.aarch64 dos2unix.aarch64 gcc.aarch64 gcc-c++.aarch64 gdb.aarch64 gzip.aarch64 iproute.aarch64 iptables.aarch64 iptables-libs.aarch64 iputils.aarch64 libXext.aarch64 libXrender.aarch64 libbabeltrace.aarch64 libblkid.aarch64 libcap.aarch64 libcap-ng.aarch64 libgcc.aarch64 libssh.aarch64 make.aarch64 net-tools.aarch64 nettle.aarch64 nginx.aarch64 openssl.aarch64 openssl-libs.aarch64 openssl-pkcs11.aarch64 seccomponent.aarch64 security-tool.aarch64 tar.aarch64 unzip.aarch64 vim-minimal.aarch64 wget.aarch64 zip.aarch64 zlib.aarch64 zlib-devel.aarch64 ...
推理基础镜像详情PyTorch(Ascend)
ModelArts提供了以下PyTorch(Ascend)推理基础镜像:
引擎版本一:pytorch_1.8.1-cann_5.1.0-py_3.7-euler_2.8.3-aarch64
- 镜像地址:swr.{region_id}.myhuaweicloud.com/atelier/pytorch_1_8_ascend:pytorch_1.8.1-cann_5.1.0-py_3.7-euler_2.8.3-aarch64-d910-20220715093657-9446c6a
- 镜像构建时间:20220715093657(yyyy-mm-dd-hh-mm-ss)
- 镜像系统版本:euleros 2.8.3
- cann:5.1.0
- Python解释器路径及版本:/home/ma-user/anaconda3/envs/PyTorch-1.8.1/bin/python, python 3.7.10
- 三方包安装路径:/home/ma-user/anaconda3/envs/PyTorch-1.8.1/lib/python3.7/site-packages
- 部分pip安装包列表:
Cython 0.29.14 Flask 2.0.1 grpcio 1.26.0 gunicorn 20.1.0 h5py 2.10.0 hccl 0.1.0 ipykernel 6.7.0 Jinja2 3.0.1 Keras 2.3.1 Keras-Applications 1.0.8 Keras-Preprocessing 1.1.2 lxml 4.4.2 matplotlib 3.5.1 matplotlib-inline 0.1.3 mmcv 0.2.14 modelarts-mindspore-model-server 1.0.4 moxing-framework 2.0.1.rc0.ffd1c0c8 numpy 1.21.2 opencv-python 4.2.0.34 pandas 0.24.2 Pillow 9.2.0 pip 22.1.2 protobuf 3.11.3 psutil 5.7.0 pycocotools 2.0.0 PyYAML 5.3.1 requests 2.27.1 scikit-image 0.17.2 scikit-learn 0.20.0 scipy 1.3.3 setuptools 63.1.0 Shapely 1.8.2 tensorflow-probability 0.10.1 torch 1.8.1+ascend.rc1.20220409 torch-npu 1.8.1rc1.post20220409 torchvision 0.9.1 tornado 6.2 tqdm 4.46.1 urllib3 1.26.10 wheel 0.37.1 zipp 3.8.1 ...
- 部分apt安装包列表:
ca-certificates.noarch cmake.aarch64 compat-openssl10.aarch64 curl.aarch64 dos2unix.aarch64 gcc.aarch64 gcc-c++.aarch64 gdb.aarch64 gzip.aarch64 iproute.aarch64 iptables.aarch64 iptables-libs.aarch64 iputils.aarch64 libXext.aarch64 libXrender.aarch64 libbabeltrace.aarch64 libblkid.aarch64 libcap.aarch64 libcap-ng.aarch64 libgcc.aarch64 libssh.aarch64 make.aarch64 net-tools.aarch64 nettle.aarch64 nginx.aarch64 openssl.aarch64 openssl-libs.aarch64 openssl-pkcs11.aarch64 seccomponent.aarch64 security-tool.aarch64 tar.aarch64 unzip.aarch64 vim-minimal.aarch64 wget.aarch64 zip.aarch64 zlib.aarch64 zlib-devel.aarch64 ...
推理基础镜像详情Mindspore(Ascend)
ModelArts提供了以下Mindspore(Ascend)推理基础镜像:
引擎版本一:mindspore_1.7.0-cann_5.1.0-py_3.7-euler_2.8.3-aarch64
- 镜像地址:swr.{region_id}.myhuaweicloud.com/atelier/mindspore_1_7_0:mindspore_1.7.0-cann_5.1.0-py_3.7-euler_2.8.3-aarch64-d910-20220715093657-9446c6a
- 镜像构建时间:20220715093657(yyyy-mm-dd-hh-mm-ss)
- 镜像系统版本:euleros 2.8.3
- cann:5.1.0
- Python解释器路径及版本:/home/ma-user/anaconda3/envs/MindSpore/bin/python, python 3.7.10
- 三方包安装路径:/home/ma-user/anaconda3/envs/MindSpore/lib/python3.7/site-packages
- 部分pip安装包列表:
Cython 0.29.14 Flask 2.0.1 grpcio 1.47.0 gunicorn 20.1.0 h5py 2.10.0 huaweicloud-sdk-python-modelarts-dataset 0.1.5 ipykernel 6.7.0 Jinja2 3.0.1 Keras 2.3.1 Keras-Applications 1.0.8 Keras-Preprocessing 1.1.2 lxml 4.4.2 matplotlib 3.5.1 mindarmour 1.7.0 mindinsight 1.7.0 mindspore-ascend 1.7.0 mmcv 0.2.14 modelarts-mindspore-model-server 1.0.4 moxing-framework 2.0.1.rc0.ffd1c0c8 numpy 1.21.2 opencv-python 4.2.0.34 pandas 1.1.3 Pillow 9.2.0 pip 22.1.2 protobuf 4.21.2 psutil 5.7.0 pycocotools 2.0.0 PyYAML 5.3.1 scikit-image 0.17.2 scikit-learn 0.24.0 scipy 1.5.4 setuptools 63.1.0 tensorboard 1.15.0 tensorflow 1.15.0 tensorflow-estimator 1.15.1 tensorflow-probability 0.10.1 tqdm 4.46.1 urllib3 1.26.10 wheel 0.37.1 zipp 3.8.1 ...
- 部分apt安装包列表:
ca-certificates.noarch cmake.aarch64 compat-openssl10.aarch64 curl.aarch64 dos2unix.aarch64 gcc.aarch64 gcc-c++.aarch64 gdb.aarch64 gzip.aarch64 iproute.aarch64 iptables.aarch64 iptables-libs.aarch64 iputils.aarch64 libXext.aarch64 libXrender.aarch64 libbabeltrace.aarch64 libblkid.aarch64 libcap.aarch64 libcap-ng.aarch64 libgcc.aarch64 libssh.aarch64 make.aarch64 net-tools.aarch64 nettle.aarch64 nginx.aarch64 openssl.aarch64 openssl-libs.aarch64 openssl-pkcs11.aarch64 seccomponent.aarch64 security-tool.aarch64 tar.aarch64 unzip.aarch64 vim-minimal.aarch64 wget.aarch64 zip.aarch64 zlib.aarch64 zlib-devel.aarch64 ...