Download Latest Version director_ai-3.11.1.tar.gz (511.8 kB)
Email in envelope

Get an email when there's a new version of director-ai

Home / v1.4.0
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2026-03-01 902 Bytes
v1.4.0 -- Batched NLI + ONNX Runtime source code.tar.gz 2026-03-01 1.4 MB
v1.4.0 -- Batched NLI + ONNX Runtime source code.zip 2026-03-01 1.5 MB
Totals: 3 Items   2.9 MB 0

What's New

Batched NLI Inference (3-5x faster)

score_batch() and score_chunked() now run a single padded forward pass instead of sequential calls. Chunked document scoring is 3-5x faster.

ONNX Export + Runtime (~30-50ms/chunk GPU)

  • export_onnx() converts FactCG model to ONNX via optimum (handles DeBERTa disentangled attention)
  • NLIScorer(backend="onnx", onnx_path=...) runs inference via ONNX Runtime with auto-CUDA detection
  • New optional dep: pip install director-ai[onnx]

Other

  • ascore_batch() async helper for batched scoring
  • AggreFact benchmark predictor now batches SummaC source chunks
  • GPU device handling fix in _model_score() — inputs now move to model device

Stats

  • 680 tests passing (Python 3.10/3.11/3.12)
  • Rust crates: all green
  • Lint + type check: clean

Full Changelog: https://github.com/anulum/director-ai/compare/v1.3.0...v1.4.0

Source: README.md, updated 2026-03-01