batch

type Batch struct {
	// InputIDs is the input token IDs for this forward pass, shape (B, L).
	InputIDs *mlx.Array

	// SeqOffsets gives each row's current position within its sequence —
	// where the chunk in InputIDs starts. Length equals the batch dimension
	// of InputIDs.
	SeqOffsets []int32

	// SeqQueryLens is each row's real query length in this forward. Values
	// less than L mean the row's tail is padding that must be masked out.
	// Length equals the batch dimension of InputIDs.
	SeqQueryLens []int32

	// Memo is per-forward memoization used to cache results, such as masks,
	// which are often the same across layers.
	Memo Memo
}

type Memo struct {
	// contains filtered or unexported fields
}