Starlings.Generation.OnnxGenAI
Text generation on ONNX Runtime GenAI 0.17.1 behind a Starling adapter: model loading with explicit provider selection (no silent fallback, TF32 off by default), runtime config overlays, reference-counted disposal, and an owned decode loop over pre-tokenized ids (greedy or seeded sampling, max new tokens, stop token ids and stop strings, streaming with UTF-8-safe incremental detokenization through the owned tokenizer Starlings.Tokenizers, cancellation between decode steps, usage accounting). References only Microsoft.ML.OnnxRuntimeGenAI.Managed: the application adds Microsoft.ML.OnnxRuntimeGenAI (CPU) or Microsoft.ML.OnnxRuntimeGenAI.Cuda. Maturity is per model profile (Stable, Preview or Experimental): see the README, generated from the model registry.
Activity
- Latest release
- 1w ago
- Total releases
- 3
- Cadence
- ~2 days
- Last 12 months
- 3
Details
- License
- MIT OR Apache-2.0
- First release
- Oct 14, 2026
| Version | Released | |
|---|---|---|
0.3.0
minor
| ||
0.2.0
initial
| ||
0.1.0-preview.6
pre
|