A  B  C  D  E  F  G  H  I  L  M  O  P  R  S  T  W  Z 

O

OnnxAdapter - class in ai.zerogpu.android.sdk.adapter.onnx
One ONNX adapter: tokenize with the HuggingFace tokenizer (standard tokenizer.json), run the model with ONNX Runtime, then decode the output tensors into opaque JSON with a small, bounded per-kind decoder.
OnnxAdapterFactory - class in ai.zerogpu.android.sdk.adapter.onnx
The ONNX engine, backed by Microsoft ONNX Runtime (inference) + the HuggingFace tokenizer (reads the standard tokenizer.json).
OnnxAdapterFactory.Companion - class in ai.zerogpu.android.sdk.adapter.onnx.OnnxAdapterFactory
 
OnnxEngine - class in ai.zerogpu.android.sdk.adapter.onnx
Self-registers the ONNX Runtime-backed ONNX engine with the AdapterRegistry at startup.
OnnxKinds - class in ai.zerogpu.android.sdk.adapter.onnx
Canonical ONNX inference kinds — the exact inference_kind DB enum values the SDK routes on.
open(File) - function in ai.zerogpu.android.sdk.adapter.gguf.LlamaRuntime.Companion
 
A  B  C  D  E  F  G  H  I  L  M  O  P  R  S  T  W  Z