From 78df3327a1e629c07952d2d106401aff9eb1bb09 Mon Sep 17 00:00:00 2001 From: Hansong Zhang Date: Tue, 23 Jul 2024 10:39:40 -0700 Subject: [PATCH] Android update prebuilt library link (#4362) Summary: 0.2 -> 0.3 Pull Request resolved: https://github.com/pytorch/executorch/pull/4362 Reviewed By: lucylq Differential Revision: D60122223 Pulled By: kirklandsign fbshipit-source-id: 2bb18f27ca819a021ca92ebb18d3b10ef6d0abb5 --- docs/source/android-prebuilt-library.md | 15 ++++++++------- .../android/LlamaDemo/download_prebuilt_lib.sh | 4 ++-- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/docs/source/android-prebuilt-library.md b/docs/source/android-prebuilt-library.md index 7bf6de1c23..ee6c2cd65e 100644 --- a/docs/source/android-prebuilt-library.md +++ b/docs/source/android-prebuilt-library.md @@ -4,17 +4,18 @@ We provide two prebuilt Android libraries (AAR), `executorch.aar` for generic us ## Contents of libraries - `executorch.aar` - - [Java library](https://github.com/pytorch/executorch/tree/release/0.2/extension/android/src/main/java/org/pytorch/executorch) - - JNI contains the JNI binding for [NativePeer.java](https://github.com/pytorch/executorch/blob/release/0.2/extension/android/src/main/java/org/pytorch/executorch/NativePeer.java) and ExecuTorch native library, including core ExecuTorch runtime libraries, XNNPACK backend, Portable kernels, Optimized kernels, and Quantized kernels. + - [Java library](https://github.com/pytorch/executorch/tree/release/0.3/extension/android/src/main/java/org/pytorch/executorch) + - JNI contains the JNI binding for [NativePeer.java](https://github.com/pytorch/executorch/blob/release/0.3/extension/android/src/main/java/org/pytorch/executorch/NativePeer.java) and ExecuTorch native library, including core ExecuTorch runtime libraries, XNNPACK backend, Portable kernels, Optimized kernels, and Quantized kernels. - Comes with two ABI variants, arm64-v8a and x86_64. - `executorch_llama.aar` - - [Java library](https://github.com/pytorch/executorch/tree/release/0.2/extension/android/src/main/java/org/pytorch/executorch) (Note: it contains the same Java classes as the previous Java, but it does not contain the JNI binding for generic Module/NativePeer Java code). - - JNI contains the JNI binding for [LlamaModule.java](https://github.com/pytorch/executorch/blob/release/0.2/extension/android/src/main/java/org/pytorch/executorch/LlamaModule.java) and ExecuTorch native library, including core ExecuTorch runtime libraries, XNNPACK backend, Portable kernels, Optimized kernels, Quantized kernels, and LLAMA-specific Custom ops library. + - [Java library](https://github.com/pytorch/executorch/tree/release/0.3/extension/android/src/main/java/org/pytorch/executorch) (Note: it contains the same Java classes as the previous Java, but it does not contain the JNI binding for generic Module/NativePeer Java code). + - JNI contains the JNI binding for [LlamaModule.java](https://github.com/pytorch/executorch/blob/release/0.3/extension/android/src/main/java/org/pytorch/executorch/LlamaModule.java) and ExecuTorch native library, including core ExecuTorch runtime libraries, XNNPACK backend, Portable kernels, Optimized kernels, Quantized kernels, and LLAMA-specific Custom ops library. - Comes with two ABI variants, arm64-v8a and x86_64. ## Downloading AAR -[executorch.aar](https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.2.1/executorch.aar) (sha1sum: af7690394fd978603abeff40cf64bd2df0dc793a) -[executorch_llama.aar](https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.2.1/executorch-llama.aar) (sha1sum: 2973b1c41aa2c2775482d7cc7c803d0f6ca282c1) +[executorch.aar](https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.3/executorch.aar) +[executorch_llama.aar](https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.3/executorch-llama.aar) +[SHA1SUMS](https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.3/SHA1SUMS) ## Using prebuilt libraries @@ -23,7 +24,7 @@ To add the Java library to your app, simply download the AAR, and add it to your In your app working directory, such as example executorch/examples/demo-apps/android/LlamaDemo, ``` mkdir -p app/libs -curl https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.2.1/executorch-llama.aar -o app/libs/executorch.aar +curl https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.3/executorch-llama.aar -o app/libs/executorch.aar ``` And include it in gradle: diff --git a/examples/demo-apps/android/LlamaDemo/download_prebuilt_lib.sh b/examples/demo-apps/android/LlamaDemo/download_prebuilt_lib.sh index 43e2bcc14d..61c86a92f7 100644 --- a/examples/demo-apps/android/LlamaDemo/download_prebuilt_lib.sh +++ b/examples/demo-apps/android/LlamaDemo/download_prebuilt_lib.sh @@ -7,8 +7,8 @@ set -eu -AAR_URL="https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.2.1/executorch-llama.aar" -AAR_SHASUM="2973b1c41aa2c2775482d7cc7c803d0f6ca282c1" +AAR_URL="https://ossci-android.s3.us-west-1.amazonaws.com/executorch/release/0.3/executorch-llama.aar" +AAR_SHASUM="f06cc1606e5e05f00fd0ae721f5d37d56124fd28" LIBS_PATH="$(dirname "$0")/app/libs" AAR_PATH="${LIBS_PATH}/executorch-llama.aar"