Download Latest Version Version 2.11.0 source code.tar.gz (8.0 MB)
Email in envelope

Get an email when there's a new version of AIMET

Home / 2.9.0
Name Modified Size InfoDownloads / Week
Parent folder
aimet_tf-2.9.0+cpu-cp310-cp310-manylinux_2_34_x86_64.whl 2025-07-01 5.5 MB
0
aimet_onnx-2.9.0+cpu-cp310-cp310-manylinux_2_34_x86_64.whl 2025-07-01 1.0 MB
0
aimet_onnx-2.9.0+cu121-cp310-cp310-manylinux_2_34_x86_64.whl 2025-07-01 33.4 MB
0
aimet_tf-2.9.0+cu118-cp310-cp310-manylinux_2_34_x86_64.whl 2025-07-01 16.2 MB
0
aimet_torch-2.9.0+cpu-py38-none-any.whl 2025-07-01 1.4 MB
0
aimet_torch-2.9.0+cu121-py38-none-any.whl 2025-07-01 9.4 MB
0
README.md 2025-07-01 890 Bytes
0
Version 2.9.0 source code.tar.gz 2025-07-01 7.5 MB
0
Version 2.9.0 source code.zip 2025-07-01 8.9 MB
0
Totals: 9 Items   83.4 MB 0

What's Changed

  • Bug Fixes and Improvements
    • ONNX
      • Rename QuantizeLinear outputs from <...>_int to <...>_q in onnx QDQ export (e78dbec)
      • Preserve I/O names in onnx QDQ export (35ad990)
      • Allow freezing loaded encodings in load_encodings_to_sim (911af75)
      • Represent activation QDQ with uint in encodings 2.0.0 in onnx QDQ export (92f63f5)
      • Allow aimet-onnx to load partial encodings (6636515)
      • Fix onnx sim.export permanently removing quantizers (9a2a407)
      • Fix onnx QDQ export output name swapping bug (6d1664c)
      • Switch AdaRound API naming to num_iterations (fea395f)
    • PyTorch
      • Add native support for Mistral-0.3 (db99447)
      • AdaScale: Update the learning rates for AdaScale learnable parameters (7336ead)
    • common
      • Add docs to build aimet from source (ae981f7)
Source: README.md, updated 2025-07-01