Skip to content

Technical Preview

Pre-release
Pre-release
Compare
Choose a tag to compare
@luluman luluman released this 20 May 18:18
· 4014 commits to master since this release
v1.1-beta.0
400a0dc

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.
Assets 3
Loading