v1.6.0

• Support ONNX model of OPSET 12~19
• Support custom operators (including CPU and GPU)
• Optimization operators support such as dynamic weighted convolution, Layernorm, RoiAlign, Softmax, ReduceL2, Gelu, GLU, etc.
• Added support for python3.7/3.9/3.11
• Add rknn_convert function
• Optimize transformer support
• Optimize the MatMul API, such as increasing the K limit length, RK3588 adding int4 * int4 -> int16 support, etc.
• Optimize RV1106 rknn_init initialization time, memory consumption, etc.
• RV1106 adds int16 support for some operators
• Fixed the problem that the convolution operator of RV1106 platform may make random errors in some cases.
• Optimize user manual
• Reconstruct the rknn model zoo and add support for multiple models such as detection, segmentation, OCR, and license plate recognition.

v1.5.2

• Improve transformer support
• Improve dynamic shape support
• Remove the target_platform default parameter of rknn.config
• Improve operator support such as GRU/LSTM/softmax/maxpool
• Improve large resolution model support
• Improve LLM support
• Improve multi-batch support