Ternary2BitTensorData

Ternary tensor data using 2-bit encoding compatible with TQ2_0 format.

Encoding scheme (matches GGUF TQ2_0):

This is the simpler ternary format with 4 values per byte.

initialShape

the shape of the tensor

data

the packed byte array (4 ternary values per byte)

scale

the scale factor for FP32 dequantization

Constructors

constructor(initialShape: Shape, data: ByteArray, scale: Float = 1.0f)

open override val blockCount: Int

Number of blocks in this storage.

open override val blockSize: Int

Number of logical elements per block.

The physical encoding describing the block layout.

open override val packedData: ByteArray

Access to the underlying packed byte array for efficient kernel operations. The packing format is implementation-defined.

open override val scale: Float

open override val shape: Shape

The shape descriptor that defines the dimensionality and size of this tensor data.

open override fun dequantizeBlock(blockIdx: Int, output: FloatArray, outputOffset: Int = 0)

Dequantize a single block to float values.

open operator override fun get(vararg indices: Int): Byte

Retrieves an element at the specified multidimensional indices.

open operator override fun set(vararg indices: Int, value: Byte)

Setter