![]() ![]() Build switch to disable usage of abseil library to remove dependency. ![]() Mac M1 support in Python and Java packages.#RECOMPOSE LIQUID NOTES V1.5.2.1 WIN MAC# Quantization tool: improved ONNX shape inference for large models.Improved the thread job partition for QLinearConv, demonstrating up to ~20% perf gain for certain models.Specialized kernel to improve performance of quantized Resize by up to 2x speedup.New quantized kernels for weight symmetry to improve performance on ARM64 little core (GEMM and Conv).Memory usage reduction through use of containers from the abseil library, especially inlined vectors used to store tensor shapes and inlined hash maps.CPU usage savings for infrequent inference requests by reducing thread spinning.Memory optimizations to support compute-intensive real-time inferencing scenarios (e.g.Operator performance optimizations, including GatherElements.Improved C++ APIs that now utilize RAII for better memory management.onnxruntime-openvino package available on Pypi (from Intel).NOTE: netstandard1.1 support is being deprecated in this release and will be removed in the 1.13 release.Additional target frameworks: net6.0, net6.0-android, net6.0-ios, net6.0-macos. Provide option to share execution context memory between TensorRT subgraphs.Workaround long CI test time caused by frequent initialization/de-initialization of TensorRT builder.Improve subgraph partitioning and consolidate TensorRT subgraphs when possible.Refactor engine cache serialization/deserialization logic.#RECOMPOSE LIQUID NOTES V1.5.2.1 WIN MAC#. ![]()
0 Comments
Leave a Reply. |