Lines Matching +full:multi +full:- +full:function
5 - RK3566/RK3568
6 - RK3588/RK3588S
7 - RV1103/RV1106
8 - RK3562
11 …rknn model must be generated using RKNN Toolkit 2: https://github.com/rockchip-linux/rknn-toolkit2
15 https://github.com/rockchip-linux/rknn-toolkit
17 https://github.com/rockchip-linux/rknpu
25 - Support RK3562
26 - Support more NPU operator fuse, such as Conv-Silu/Conv-Swish/Conv-Hardswish/Conv-sigmoid/Conv-Har…
27 - Improve support for NHWC output layout
28 - RK3568/RK3588：The maximum input resolution up to 8192
29 - Improve support for Swish/DataConvert/Softmax/Lstm/LayerNorm/Gather/Transpose/Mul/Maxpool/Sigmoid…
30 - Improve support for CPU operators (Cast, Sin, Cos, RMSNorm, ScalerND, GRU)
31 - Limited support for dynamic resolution
32 - Provide MATMUL API
33 - Add RV1103/RV1106 rknn_server application as proxy between PC and board
34 - Add more examples such as rknn_dynamic_shape_input_demo and video demo for yolov5
35 - Bug fix
41 - Support more NPU operators, such as Reshape、Transpose、MatMul、 Max、Min、exGelu、exSoftmax13、Resize e…
42 - Add **Weight Share** function, reduce memory usage.
43 - Add **Weight Compression** function, reduce memory and bandwidth usage.(RK3588/RV1103/RV1106)
44 - RK3588 supports storing weights or feature maps on SRAM, reducing system bandwidth consumption.
45 - RK3588 adds the function of running a single model on multiple cores at the same time.
46 - Add new output layout NHWC (C has alignment restrictions) .
47 - Improve support for non-4D input.
48 - Add more examples such as rknn_yolov5_android_apk_demo and rknn_internal_mem_reuse_demo.
49 - Bug fix.
53 - Support RV1103/RV1106（Beta SDK）
54 - rknn_tensor_attr support w_stride(rename from stride) and h_stride
55 - Rename rknn_destroy_mem()
56 - Support more NPU operators, such as Where, Resize, Pad, Reshape, Transpose etc.
57 - RK3588 support multi-batch multi-core mode
58 - When RKNN_LOG_LEVEL=4, it supports to display the MACs utilization and bandwidth occupation of ea…
59 - Bug fix
63 - Support RK3588
64 - Support more operators, such as GRU、Swish、LayerNorm etc.
65 - Reduce memory usage
66 - Improve zero-copy interface implementation
67 - Bug fix
71 - Support INT8+FP16 mixed quantization to improve model accuracy
72 - Support specifying input and output dtype, which can be solidified into the model
73 - Support multiple inputs of the model with different channel mean/std
74 - Improve the stability of multi-thread + multi-process runtime
75 - Support flashing cache for fd pointed to internal tensor memory which are allocated by users
76 - Improve dumping internal layer results of the model
77 - Add rknn_server application as proxy between PC and board
78 - Support more operators, such as HardSigmoid、HardSwish、Gather、ReduceMax、Elu
79 …- Add LSTM support (structure cifg and peephole are not supported, function: layernormal, clip is …
80 - Bug fix
84 - Optimize the performance of rknn_inputs_set()
85 - Add more functions for zero-copy
86 - Add new OP support, see OP support list document for details.
87 - Add multi-process support
88 - Support per-channel quantitative model
89 - Bug fix
93 …- Optimize the performance of rknn_inputs_set(), especially for models whose input width is 8-byte…
94 - Add new OP support, see OP support list document for details.
95 - Bug fix
98 - Initial version