Skip to content

Version 2.24.0

Choose a tag to compare

View all tags
@aimetci aimetci released this 10 Feb 04:59
2.24.0
2ec4261
  • 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)
Assets 10
Loading