ForwardResult class

A graph's raw output for one input: a flat, row-major buffer plus its tensor shape.

shape is one of two layouts a graph can hand back — see pooling.dart's meanPoolAndNormalize for how each is turned into a single embedding vector:

• [1, dim] — already pooled by the engine (e.g. a LiteRT compiled model whose graph itself produces one vector per input). Treated as a pass-through.
• [1, seq, dim] — per-token hidden states. Mean-pooled over the seq axis (optionally respecting an attention mask) before normalizing.

Constructors

ForwardResult({required List<double> values, required List<int> shape, List<int>? attentionMask})

const

Properties

attentionMask → List<int>?

The effective attention mask over this result's seq axis, when the graph knows one (design D-T3's silent-regression fix). A runTokens that pads a fixed-shape graph MUST pad ids/mask/type-ids together and echo the padded mask here, so the masked mean-pool excludes exactly the padding it added — never the tokenizer's mask, which describes the UNPADDED input. One over a dynamic-shape graph (no padding) may pass the input mask through unchanged or omit it — finalizeEmbedding's caller then falls back to the tokenizer's mask.

final

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

shape → List<int>

Tensor shape, e.g. [1, dim] or [1, seq, dim].

final

values → List<double>

Flat, row-major buffer. values.length == shape.reduce((a, b) => a * b).

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