RuntimeConfig class

Runtime config for building a model — the per-call params getActiveModel collects, kept as a small holder so the provider contract stays stable as params evolve.

Constructors

RuntimeConfig({required int maxTokens, required String modelPath, String? tokenizerPath, PreferredBackend? preferredBackend, PreferredBackend? preferredVisionBackend, PreferredBackend? preferredAudioBackend, bool supportImage = false, bool supportAudio = false, int? maxNumImages, bool? enableSpeculativeDecoding, int? maxConcurrentSessions, List<int>? loraRanks, Map<String, String>? artifactPaths, String? language})

const

Properties

artifactPaths → Map<String, String>?

filename → on-disk path for a multi-file model bundle (TTS). The bundle backend resolves each graph/dictionary/embedding file by name from this map. Null for single-file models (inference/embedding/STT).

final

enableSpeculativeDecoding → bool?

final

hashCode → int

The hash code for this object.

no setter, inherited

language → String?

TTS-only (Qwen3): the language to condition generation on — one of flutter_gemma_speech's qwen3SupportedLanguages, or 'auto'. Null for non-TTS models, and for TTS models with no language parameter (e.g. Matcha, whose locale comes from its TtsModelProfile.locale instead) — the TTS backend defaults a null value to 'english'. Not validated here; the TTS backend rejects an unsupported value with ArgumentError before loading the model.

final

loraRanks → List<int>?

LoRA ranks for the MediaPipe path; null falls back to the platform's supportedLoraRanks. Carried in the config so the (cached) default-engine build closure reads it per call instead of capturing a stale local.

final

maxConcurrentSessions → int?

final

maxNumImages → int?

final

maxTokens → int

final

modelPath → String

Resolved on-disk path to the model file. Core's platform createModel preamble resolves it from the active spec via the model manager and passes it here so the engine package never touches core's file-path resolution.

final

preferredAudioBackend → PreferredBackend?

Backend for the AUDIO encoder, independent of preferredBackend. Null defaults to CPU in the LiteRT-LM engine as a conservative default — but, unlike the vision encoder, the audio encoder runs fine on GPU and is often faster there (Gemma 3n audio is ~2× CPU on Metal), so set it to PreferredBackend.gpu for speed. Ignored by MediaPipe.

final

preferredBackend → PreferredBackend?

final

preferredVisionBackend → PreferredBackend?

Backend for the VISION encoder, independent of preferredBackend (the text/decoder backend). Null defaults to CPU in the LiteRT-LM engine, because the vision encoder's STABLEHLO_COMPOSITE ops fail to prepare on the Metal/WebGPU delegates (LiteRT-LM#2461). Set it (e.g. to PreferredBackend.gpu) only for a model whose vision section bakes a gpu-only backend_constraint. Ignored by the MediaPipe engine (whole-model backend, no per-encoder split).

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

supportAudio → bool

final

supportImage → bool

final

tokenizerPath → String?

Resolved on-disk path to the tokenizer. Used by embedding and STT backends; null for inference. The spec carries source identities (network/asset/file); core resolves them to on-disk paths via the model manager and passes the resolved tokenizer path here (install-vs-runtime separation).

final

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited