Download Latest Version Version 2.27.0 source code.zip (8.4 MB)
Email in envelope

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

Home / 2.24.0
Name Modified Size InfoDownloads / Week
Parent folder
aimet_onnx-2.24.0+cpu-cp310-cp310-win_amd64.whl 2026-02-10 728.5 kB
0
aimet_onnx-2.24.0+cpu-cp310-cp310-manylinux_2_34_x86_64.whl 2026-02-10 944.2 kB
0
aimet_onnx-2.24.0+cu121-cp310-cp310-manylinux_2_34_x86_64.whl 2026-02-10 79.3 MB
0
aimet_onnx-2.24.0+cpu-cp312-cp312-win_arm64.whl 2026-02-10 696.5 kB
0
aimet_onnx-2.24.0-cp310-cp310-manylinux_2_34_x86_64.whl 2026-02-10 79.3 MB
0
aimet_torch-2.24.0+cpu-py310-none-any.whl 2026-02-10 1.2 MB
0
aimet_torch-2.24.0+cu121-py310-none-any.whl 2026-02-10 8.2 MB
0
aimet_torch-2.24.0-py310-none-any.whl 2026-02-10 10.8 MB
0
README.md 2026-02-09 1.0 kB
0
Version 2.24.0 source code.tar.gz 2026-02-09 7.6 MB
0
Version 2.24.0 source code.zip 2026-02-09 8.3 MB
0
Totals: 11 Items   197.1 MB 0

  • Bug fixes and Improvements

    • ONNX

      • Add Windows ARM64 wheel build/test support, distribute Windows ARM64 wheel on GitHub releases (1390b96)
      • Add transpose MatMul support in Sequential MSE (ff7a284)

    • Torch

      • Expose block-level AdaScale API (72246db)
      • Improve numerical stability of zero point shifting ([-1.5, -.5, .5, 1.5]) implementation (489f7df)
      • Fix :func:replace_lora_layers_with_quantizable_layers to inherit train/eval flag (af5a82d)
      • Fix SpinQuant evaluation by untying lm_head and embed_tokens prior to loading the state_dict (47f574d)
      • Experimental - Implement Progressive Gradient Scaling (PGS) support for Triton-based quantization kernels (b58b00b)

    • Common

      • Fix TFEnhanced incorrectly producing negative scales when encountering empty (size‑0) inputs (ea4af6a)
      • Unpin numpy dependency (8a999a1)
      • Add an alias for referencing the eNPU configuration file (b79611c)
Source: README.md, updated 2026-02-09