Releases: airockchip/rknn-toolkit2
Releases · airockchip/rknn-toolkit2
v2.3.0
v2.2.0
- Support installation via pip
- Optimize transformer model performance
- Support Python 3.12
- Operator optimization, such as softmax, hardmax, MatMul, etc.
v2.1.0
- Support RV1103B (Beta)
- Support RK2118 (Beta)
- Support Flash Attention (Only RK3562 and RK3576)
- Improve MatMul API
- Improve support for int32 and int64
- Support more operators and operator fusion
v2.0.0-beta0
- Support RK3576 (Beta)
- Support RK2118 (Beta)
- Support SDPA (Scaled Dot Product Attention) to improve transformer performance
- Improve custom operators support
- Improve MatMul API
- Improve support for Reshape,Transpose,BatchLayernorm,Softmax,Deconv,Matmul,ScatterND etc.
- Support pytorch 2.1
- Improve support for QAT models of pytorch and onnx
- Optimize automatic generation of C++ code
v1.6.0
- Support ONNX model of OPSET 12~19
- Support custom operators (including CPU and GPU)
- Improve support for dynamic weight convolution, Layernorm, RoiAlign, Softmax, ReduceL2, Gelu, GLU, etc.
- Added support for python3.7/3.9/3.11
- Add rknn_convert function
- Improve transformer support
- Improve the MatMul API, such as increasing the K limit length, RK3588 adding int4 * int4 -> int16 support, etc.
- Reduce 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.
- Improve 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
Update rknn-toolkit2/rknn-toolkit-lite2 to 1.5.2
v1.5.0
Update rknn-toolkit2/rknn-toolkit-lite2 to 1.5.0 Signed-off-by: Randall Zhuo <[email protected]>
v1.4.0: update rknn-toolkit2/rknn-toolkit-lite2 to 1.4.0
Signed-off-by: raul.rao <[email protected]>