Changelog

Changelog#

[v0.11.0.0] - 2025-09-10#

API#

  • Support torch parser

  • Yolo12l and Yolo12x support

  • Expanded support range for ViT models

  • Minor bug fixes for GRU/RNN/LSTM

[v0.10.0.0] - 2025-07-24#

API#

  • Added Inference_scheme global4/global8 modes

  • Yolov10 series, Yolo11 series, Yolo12n, Yolo12s, and Yolo12m support

  • Added LLM config options

  • Support for GRU/RNN/LSTM

[v0.9.0.5] - 2025-06-25#

API#

  • Changed YOLO model decoding to be linked with the model zoo

  • Added layer config options

[v0.9.0.4] - 2025-05-22#

API#

  • Support direct compilation of HuggingFace LLM models

[v0.9.0.3] - 2025-04-02#

API#

  • Support saving mblt using mmap

  • Support diverse visualization types

[v0.9.0.2] - 2025-01-16#

API#

  • Add API for saving model architecture

  • Support Visualization tool

  • Support Run min output difference QAT mode

[v0.9.0.1] - 2024-12-13#

API#

  • Add API for global core (beta)

  • Add API for YOLO post (beta)

  • Support diverse hardware (aries, regulus, aries2)

[v0.9.0.0] - 2024-11-27#

API#

  • Update the high-level parsing processes

Docker#

  • ONNX: 1.13.0 -> 1.16.2

  • TensorFlow: 2.9.0 -> 2.17.0

  • Torch: 1.13.0 -> 2.4.1

[v0.8.5] - 2024-06-20#

API#

  • Support FastPercentile quantization method

[v0.8.4] - 2024-05-20#

API#

  • TF backend connected to ONNX backend by TF2ONNX

  • Enable to compile models with custom input shape

  • Support more operations

Docker#

  • ONNX: 1.12.0 -> 1.13.0

[v0.8.3] - 2024-03-07#

API#

  • Support TF Lite backend

[v0.8.2] - 2024-02-23#

[v0.8.1] - 2023-12-08#

[v0.8.0] - 2023-11-02#

API#

  • TVM backend deprecated

[v0.7.12] - 2023-09-12#

[v0.7.11] - 2023-08-31#

API#

  • Support TorchScript backend

[v0.7.10] - 2023-08-11#

[v0.7.9] - 2023-08-11#

[v0.7.8] - 2023-08-08#

[v0.7] - 2023-03-23#

  • Multi-channel quantization

  • Support more operations

API#

  • Improve calibration dataset processing

  • Support CPU offloading (beta version)

[v0.6] - 2022-08-10#

  • Minor updates

[v0.5] - 2022-07-01#

Docker#

  • Conda -> Virtualenv

  • Python: 3.7.7 -> 3.8.10

  • Torch: 1.8.1 -> 1.10.1

  • TensorFlow: 1.15.0 -> 2.3.0

  • ONNX:1.6.0 -> 1.11.0

Parser#

  • Code refactoring

API#

  • Enable saving sample inference results (inputs and outputs)

[v0.4] - 2022-02-23#

Optimizer#

  • Minor updates in fusing reshape

[v0.3] - 2022-02-05#

Parser#

  • Identify preprocess and postprocess of the model

  • Exclude preprocess and postprocess if they are unsupported by the NPU

API#

  • Simulate integer inference in Python API

[v0.2] - 2021-12-01#

  • First release