代码拉取完成，页面将自动刷新
Windows Linux Android Environment Preparation Beginner Intermediate Expert
Welcome to MindSpore Lite. We provide functions such as model conversion, model inference, image processing, etc. that support multiple operating systems and hardware platforms. You can download the version package suitable for the local environment and use it directly.
| Module Name | Hardware Platform | Operating System | Download Links | SHA-256 |
|---|---|---|---|---|
| Inference/training runtime, inference aar package, and benchmark tools | CPU | Android-aarch32 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/android/cpu/mindspore-lite-1.3.0-android-aarch32.tar.gz | c1a950feec47a58871956cab74f0b6f76ad2f151dde990228782f76c0d8120df |
| Inference/training runtime, inference aar package, and benchmark tools | CPU/GPU | Android-aarch64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/android/gpu/mindspore-lite-1.3.0-android-aarch64.tar.gz | 4def68662f5b249db0fd0f372fab1877e530fe32b6b9317869f01bedde892838 |
| Inference/training runtime, inference jar package, and benchmark/codegen/converter/cropper tools | CPU | Ubuntu-x64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/linux/mindspore-lite-1.3.0-linux-x64.tar.gz | 2d0f77bb3c1a9489bc9511f334fb6cea3266d6bd4d600517b5aa7e58efab1310 |
| Inference runtime and benchmark/codegen/converter tools | CPU | Windows-x64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/windows/mindspore-lite-1.3.0-win-x64.zip | 40c1abdeb4c5f5353844e9798c6a0f20565a5a3bc6de7da3cdc4a2df6fa15ef7 |
| iOS inference runtime | CPU | iOS-aarch32 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/ios/mindspore-lite-1.3.0-ios-aarch32.tar.gz | b4bb1435887b04ce95be5429875e81c3e40a57b0c6182a35d58ea34b27d5fa5c |
| iOS inference runtime | CPU | iOS-aarch64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/ios/mindspore-lite-1.3.0-ios-aarch64.tar.gz | a28111c2bcc542a70ef98edfe007892855dcfcd9d40586fa98be962caefc26d3 |
| NNIE converter tool | CPU | Ubuntu-x64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/linux/nnie/mindspore-lite-1.3.0-linux-x64.tar.gz | 73f4dffde69d24a8d0574e771bc6131a45a8fc5ebd18b34fc7afd30a0d149cb1 |
| NNIE inference runtime and benchmark tools | Hi3516D | Linux-aarch32 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/linux/mindspore-lite-1.3.0-linux-aarch32.tar.gz | 07a0d0a8a8f257c01d06fa33f57969eb68385b430f2f5a3a4b09dba463c361d9 |
| HarmonyOS lite runtime | Hi3516D | OpenHarmony | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.3.0-lite/MindSpore/lite/release/openharmony/mindspore-lite-1.3.0-ohos-aarch32.tar.gz | 1bd481e93b6f3b2467a6d8f0bcc2da0221e4d023d74c584174dedb8854704748 |
| Module Name | Hardware Platform | Operating System | Download Links | SHA-256 |
|---|---|---|---|---|
| Inference runtime (cpp), training runtime (cpp), inference aar package, and benchmark/benchmark_train tools. | CPU | Android-aarch32 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.2.0/MindSpore/lite/release/android/mindspore-lite-1.2.0-android-aarch32.tar.gz | 7d073573385a69bff53542c395d106393da241682cd6053703ce21f1de23bac6 |
| Inference runtime (cpp), training runtime (cpp), inference aar package, and benchmark/benchmark_train tools. | CPU/GPU | Android-aarch64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.2.0/MindSpore/lite/release/android/gpu/mindspore-lite-1.2.0-android-aarch64.tar.gz | 7f8400f0b97fa3e7cbf0d266c73b43a2410905244b04d0202fab39d9267346e0 |
| Inference runtime (cpp), training runtime (cpp), inference jar package, and benchmark/benchmark_train/codegen/converter/cropper tools. | CPU | Ubuntu-x64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.2.0/MindSpore/lite/release/linux/mindspore-lite-1.2.0-linux-x64.tar.gz | 3b609ed8be9e3ae70987d6e00421ad4720776d797133e72f6952ba6b93059062 |
| Inference runtime (cpp) and benchmark/codegen/converter tools. | CPU | Windows-x64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.2.0/MindSpore/lite/release/windows/mindspore-lite-1.2.0-win-x64.zip | bf01851d7e2cde416502dce11bd2a86ef63e559f6dabba090405755a87ce14ae |
| Inference runtime(cpp) | CPU | OpenHarmony | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.2.0/MindSpore/lite/release/openharmony/mindspore-lite-1.2.0-ohos-aarch32.tar.gz | a9987b25815cb69e0f630be1388486e8d727a19815a67851089b7d633bd2f3f2 |
| Module Name | Hardware Platform | Operating System | Download Links | SHA-256 |
|---|---|---|---|---|
| MindSpore Lite Converter | CPU | Ubuntu-x64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.1.0/MindSpore/lite/release/linux/mindspore-lite-1.1.0-train-converter-linux-x64.tar.gz | f95a9db98c84ec3d97f88383ecc3832582aa9737ed287c33703deb0b419acf25 |
| MindSpore Lite Runtime (include image processing) | CPU | Android-aarch64/Android-aarch32 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.1.0/MindSpore/lite/release/android/mindspore-lite-1.1.0-train-android.tar.gz | a6d8152f4e2d674c52af2c379f7d07858d30bc0dceef1dbc366e6fa16a5948b5 |
| CPU | Ubuntu-x64 | https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.1.0/MindSpore/lite/release/linux/mindspore-lite-1.1.0-train-linux-x64.tar.gz | 1290f0adc790adc9edce654b9a629a9a323cfcb8453eb6bc19b779ef726282bf |
- Ubuntu-x64 Package is compiled in an environment where the GCC version is greater than or equal to 7.3.0, so the deployment environment requires the GLIBC version to be greater than or equal to 2.27.
- Android-aarch32 does not support GPU and NPU.
- MindSpore Lite also provides
libmindspore-lite.astatic library cropper tool for Runtime, which can crop the static library files, and effectively reduce the size of the library files.- After the download of MindSpore Lite is completed, SHA-256 integrity verification is required.
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。
