skainet-io-gguf/sk.ainet.io.gguf.llama/toQ4_0MemSeg

toQ4_0MemSeg

fun Tensor<Int8, Byte>.toQ4_0MemSeg(logicalShape: Shape, arena: Arena): Q4MemorySegmentTensorData(source)

Extension: convert raw Int8 tensor to Q4_0 MemorySegment-backed data.