Skip to content

v2.0.1

Latest
Latest

Choose a tag to compare

View all tags
@gmarcusm gmarcusm released this 01 Apr 15:35
v2.0.1
04ddb93
This commit was signed with the committer’s verified signature.
gmarcusm Guillermo Marcus
GPG key ID: 74E713F6FC10F900
Verified
Learn about vigilant mode.

Changes from v2.0.0 to v2.0.1

New Features

  • Added HARQ-IR support to LDPC5GEncoder and LDPC5GDecoder with per-redundancy-version rate-matching (TS 38.212) (PR #944)(thanks to @rabihchrabieh)

Bug Fixes

  • Fixed batch dimension corruption in LDPCBPDecoder, ViterbiDecoder, BCJRDecoder, TurboDecoder, and TurboEncoder for multi-dimensional inputs
  • Fixed float cast in RandomInterleaver and Turbo3GPPInterleaver inverse permutation
  • Fixed test data corruption from in-place-updated numpy buffers in test_3gpp_lsp.py

Improvements

  • Remove TF legacy reshapes and dtypes
  • Switched all FEC index tensors from int64 to int32

Tests

  • Relaxed torch.allclose tolerance to atol=1e-5 in signal compile tests

CI

  • Added DCO sign-off check workflow for pull requests
  • Upgraded CodeQL workflow to actions/checkout@v4 and codeql-action@v4

Documentation

  • Major update to 5G_Channel_Coding_Polar_vs_LDPC_Codes.ipynb notebook
  • Fixed non-deterministic bibliography back-references in parallel doc builds
  • Added list_registry Sphinx extension needed for sionna-rt documentation

Contributors

rabihchrabieh
Assets 2
Loading