Recent Releases of https://github.com/airockchip/rknn-toolkit2
https://github.com/airockchip/rknn-toolkit2 -
- Support for RV1126B platform
- Improved einsum and Norm operations support
- Added automatic mixed precision functionality
- Enhanced graph optimization capabilities
- C
Published by airockchip about 1 year ago
https://github.com/airockchip/rknn-toolkit2 -
RKNN-Toolkit2 support ARM64 architecture
RKNN-Toolkit-Lite2 support installation via pip
Add support for W4A16 symmetric quantization (RK3576)
Operator optimization, such as LayerNorm, LSTM, Transpose, MatMul, etc.
- C
Published by airockchip over 1 year ago
https://github.com/airockchip/rknn-toolkit2 -
- Support installation via pip
- Optimize transformer model performance
- Support Python 3.12
- Operator optimization, such as softmax, hardmax, MatMul, etc.
- C
Published by airockchip almost 2 years ago
https://github.com/airockchip/rknn-toolkit2 - 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
- C
Published by airockchip almost 2 years ago
https://github.com/airockchip/rknn-toolkit2 -
- 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
- C
Published by airockchip over 2 years ago
https://github.com/airockchip/rknn-toolkit2 - 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.
- C
Published by airockchip over 2 years ago
https://github.com/airockchip/rknn-toolkit2 - v1.5.2
Update rknn-toolkit2/rknn-toolkit-lite2 to 1.5.2
- C
Published by airockchip over 2 years ago