Skip to content

Release Notes

Choose a tag to compare

View all tags
@YifanShenSZ YifanShenSZ released this 22 Jan 03:00
· 53 commits to main since this release
8.2
1a0d051
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
  • Increase conversion support coverage for models produced by torch.export
    • All common ops have been covered, that is 83% parity with our mature torch.jit.trace converter
    • A new model supported: torchaudio wav2vec
  • A new transformers graph pass "common::scaled_dot_product_attention_sliced_q" for improved performance of sdpa calculation with long sequence lengths (e.g. Depth-Anything model, with sequence length 1814, transformed by the graph pass was 34% faster and used 45% less memory on ANE)
  • New torch ops supported
    • native_group_norm
    • bool type triu
  • Bug fixes
    • Incorrect behaviour of torch.linspace
    • Wrong power 2 - sqrt fusion when power exponent is a tensor

Special thanks to our open source community contributors for this release: @RGooBS24 @fukatani @twoertwein @kasper0406

Contributors

kasper0406, twoertwein, and 2 other contributors
Assets 20
Loading