Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Features:

Added a feature called "bmodel_checker", which aids in checking the correction and functionality of the BModels.
Supported LSTM (Long Short-Term Memory) for bm1684, indicating improved capabilities for handling sequence data.
Added support for the ONNX Loop operation, expanding the range of operations that can be performed using the ONNX format.
Implemented support for operations like 'stack', 'new_zeros', 'new_ones' in PyTorch.
Added a new visual tool for analyzing the parameters or operation of the models.
Added support for TensorFlow's MobileBert model.

Bug Fixes:

Fixed a bug related to 'decode lmem address', which might have caused issues in decoding addresses.
Addressed the 'incomplete onnx shape info' bug, improving the reliability of using ONNX format models.
Resolved an issue with 'single thread of int4 regression test', enhancing the testing suite.
Fixed the 'group deconv' and 'deconv1d' issues, optimizing the performance of deconvolution operations.
Resolved an error in the ArgError[18xx] case in 'test_onnx.py'.
Corrected an issue causing MulConst overflow in certain cases.

Code Refactoring:

Refactored BModel_dis to make it more efficient or easier to understand.
Unified the codegen pass to simplify the code generation process.
Revised the argument structure of bmodel_checker for more logical and intuitive use.
Modified the PermutePadSwap function to accommodate more situations.
Refined memory usage for large models, improving efficiency and performance.
Removed unused files and refactored main_entry, run_model, and cfg files for more streamlined execution.

Documentation Updates:

Updated the README file to provide up-to-date information.
Synced with model-zoo to maintain the relevance of documentation.
Added a description for the visual tool parameter.
Added information on mlir precision test and target in the documentation.
Updated the quick start guide for PyTorch.
Added more detailed information about the new bmodel_checker tool and Tensor Location in the documentation.

Testing and Verification:

Added an inference test for 'stable diffusion.'
Added regression tests for ONNX on the 1684 chip.
Fixed an issue in the ArgError[18xx] case in 'test_onnx.py', improving the ONNX testing suite.
Added an operation regression test for Athena2.
Added a test for 'stable diffusion' to ensure its proper functionality.

Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Features:

• Added a feature called "bmodel_checker", which aids in checking the correction and functionality of the BModels.
• Supported LSTM (Long Short-Term Memory) for bm1684, indicating improved capabilities for handling sequence data.
• Added support for the ONNX Loop operation, expanding the range of operations that can be performed using the ONNX format.
• Implemented support for operations like 'stack', 'new_zeros', 'new_ones' in PyTorch.
• Added a new visual tool for analyzing the parameters or operation of the models.
• Added support for TensorFlow's MobileBert model.

Bug Fixes:

• Fixed a bug related to 'decode lmem address', which might have caused issues in decoding addresses.
• Addressed the 'incomplete onnx shape info' bug, likely improving the reliability of using ONNX format models.
• Resolved an issue with 'single thread of int4 regression test', enhancing the testing suite.
• Fixed the 'group deconv' and 'deconv1d' issues, optimizing the performance of deconvolution operations.
• Resolved an error in the ArgError[18xx] case in 'test_onnx.py'.
• Corrected an issue causing MulConst overflow in certain cases.

Code Refactoring:

• Refactored BModel_dis to make it more efficient or easier to understand.
• Unified the codegen pass to simplify the code generation process.
• Revised the argument structure of bmodel_checker for more logical and intuitive use.
• Modified the PermutePadSwap function to accommodate more situations.
• Refined memory usage for large models, improving efficiency and performance.
• Removed unused files and refactored main_entry, run_model, and cfg files for more streamlined execution.

Documentation Updates:

• Updated the README file to provide up-to-date information.
• Synced with model-zoo to maintain the relevance of documentation.
• Added a description for the visual tool parameter.
• Added information on mlir precision test and target in the documentation.
• Updated the quick start guide for PyTorch.
• Added more detailed information about the new bmodel_checker tool and Tensor Location in the documentation.

Testing and Verification:

• Added an inference test for 'stable diffusion.'
• Added regression tests for ONNX on the 1684 chip.
• Fixed an issue in the ArgError[18xx] case in 'test_onnx.py', improving the ONNX testing suite.
• Added an operation regression test for Athena2.
• Added a test for 'stable diffusion' to ensure its proper functionality.
• Fixed the issue with the daily build test, ensuring a more reliable continuous integration pipeline.

Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Notable changes:

1. Lots of bug fixes and performance improvements.
2. TPU-MLIR supports importing Pytorch models (no need to convert to ONNX).
3. Unified pre-processing for bm168x and cv18xx chips.
4. Support for the bm1684 chip is underway.

Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Notable changes:

• Resolved pre-processing performance issues.
• Added shape inference for dynamic input shapes.
• Implemented constant folding to simplify the graph.
• Improved performance, still working on optimizations.

Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Notable changes:

1. The image pre-processing will be offloaded to TPU, improving performance.
2. Many bug fixes allow TPU-MLIR to support more neural networks.

• fix pool sign error in v0.8-beta.3

Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Notable changes:

1. The image pre-processing will be offloaded to TPU, improving performance.
2. Many bug fixes allow TPU-MLIR to support more neural networks.

• Fix pre-processing conversion bug in v0.8-beta.2

Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Notable changes:

1. The image pre-processing will be offloaded to TPU, improving performance.
2. Many bug fixes allow TPU-MLIR to support more neural networks.

* Fix reading pre-processing configuration bug in v0.8-beta.1

Technical Preview

This beta version of TPU-MLIR is for testing purposes only—do not use it in production.

Notable changes:

1. The image pre-processing will be offloaded to TPU, improving performance.
2. Many bug fixes allow TPU-MLIR to support more neural networks.

Technical Preview

This is a beta version of the TPU-MLIR. Please don't use it for a production environment.

With this version, some changes should be highlighted:

1. Optimize the layer group process with much performance improvement.
2. With many bug fixes, TPU-MLIR can support more Neural networks.

---

Welcome to TPU-MLIR. To get a start, you can:

Follow the Readme to understand how to use TPU-MLIR: https://github.com/sophgo/tpu-mlir
Read the design of TPU-MLIR: https://arxiv.org/abs/2210.15016
Understand the development plan: https://github.com/sophgo/tpu-mlir/wiki/Roadmap%5BCN%5D
Understand the project structure: https://github.com/sophgo/tpu-mlir/wiki/Tutorial%5BCN%5D
Try to solve the "good first issue" issues from https://github.com/sophgo/tpu-mlir/issues; they are relatively small and will gradually increase.
https://github.com/PaddlePaddle/FastDeploy has many PaddlePaddle models; you can get familiar with TPU-MLIR by adapting the model. (please be sure to convert the PaddlePaddle model to ONNX format first.).
For technical details, please refer to: https://tpumlir.org/docs/developer_manual/index.html.
Any questions and suggestions are welcome; everyone can exchange opinions and learn together.

Release candidate

Welcome to TPU-MLIR. To get a start, you can:

1. Follow the Readme to understand how to use TPU-MLIR: https://github.com/sophgo/tpu-mlir
2. Read the design of TPU-MLIR: https://arxiv.org/abs/2210.15016
3. Understand the development plan: https://github.com/sophgo/tpu-mlir/wiki/Roadmap%5BCN%5D
4. Understand the project structure: https://github.com/sophgo/tpu-mlir/wiki/Tutorial%5BCN%5D
5. Try to solve the "good first issue" issues from https://github.com/sophgo/tpu-mlir/issues; they are relatively small and will gradually increase.
6. https://github.com/PaddlePaddle/FastDeploy has many PaddlePaddle models; you can get familiar with TPU-MLIR by adapting the model. ( attention: converting the PaddlePaddle model to ONNX format first.).
7. For technical details, please refer to: https://tpumlir.org/docs/developer_manual/index.html
8. Any questions and suggestions are welcome; everyone can exchange opinions and learn together.