Release 2.1.3
Major Features and Improvements
-
Updated CMake build rules to support both CompiledModel and Interpreter APIs. cmake_example/CMakeLists.txt shows how you can use both libraries.
-
Expanded MediaTek NPU support to all applicable Android versions (only Android 15 previously) by supporting bundling MediaTek libraries in application binary.
-
Added experimental support for multi-threaded CompiledModel creation
-
Fixed GPU support for Python on Windows
-
Individual Options APIs (litert/cc/options) no longer use LiteRT C APIs (LiteRtXXX). They’re updated to use string based serialization and use LrtXXX() functions which can be linked individually.
-
Added basic support for Broadcom VideoCore GPUs.
Bug Fixes and Other Changes
-
Move the experimental API
GetProfiler()out oflitert::CompiledModel. -
Fixed a bug that given CPU Buffers are not always synced with GPU Accelerator from the second inference.
-
Removed methods from
litert::Eventwhich uses C typeLiteRtEnvironment. All C++ API should uses C++litert::Environmentinstead. Also removed methodCreateFromSyncFenceFd()that doesn't acceptlitert::Environment. -
Updated
litert::Event::Type()to return C++ types instead of C types. -
The LiteRT headers no longer define the following OpenCL type names in the global namespace when OpenCL is not supported:
cl_mem,cl_event. These have been replaced with the type aliasesLiteRtClMemandLiteRtClEvent, defined in a new headerlitert/c/litert_opencl_types.h. All of these symbols that didn't include theLiteRtprefix in their name were never intended to be part of the LiteRT API, and their presence in the global namespace risked conflicts with header files from other packages. -
Likewise, and for the same reason, the LiteRT headers no longer define the following WebGPU type names in the global namespace when WebGPU is supported:
struct WGPUBufferImpl,WGPUBuffer. These have been replaced with the type aliasLiteRtWGPUBufferwhich is defined in a new header filelitert/c/litert_webgpu_types.h. Alternatively, apps using these symbols can get them from WebGPU'swebgpu.hheader file. -
Added experimental support for multi-threaded CompiledModel creation