Method EncodeBatch

Namespace

Qavren.Edge.Embeddings.Onnx

Assembly

Qavren.Edge.Embeddings.Onnx.dll

EncodeBatch(IReadOnlyList<string>, int, IReadOnlyList<int>)

Encodes, truncates, right-pads to the smallest configured bucket that fits the batch maximum, and synthesises the attention mask.

The returned batch's three long[] are rented from ArrayPool<T>.Shared and are valid over their first Qavren.Edge.Embeddings.Onnx.TokenizedBatch.TensorLength elements only. The generator hands them back once the OrtValues built over them are disposed; a caller outside this package simply drops the batch and the GC reclaims the buffers without them ever re-entering the pool.

TokenizedBatch EncodeBatch(IReadOnlyList<string> texts, int maxSequenceLength, IReadOnlyList<int> buckets)

Parameters

texts IReadOnlyList<string>

The inputs, already prefixed by the caller.

maxSequenceLength int

The preset's ceiling.

buckets IReadOnlyList<int>

The preset's sequence buckets, ascending.

Returns

TokenizedBatch

One padded batch.