GgufParametersLoader

class GgufParametersLoader(sourceProvider: () -> Source, onProgress: (current: Long, total: Long, message: String?) -> Unit = { _, _, _ -> }) : ParametersLoader(source)

ParametersLoader implementation backed by GGUFReader.

Notes:

Currently supports loading tensors as FP32 or Int32. Other dtypes can be added as needed.
For quantized GGML tensor payloads, this implementation does not perform dequantization and will throw.
A lightweight progress callback can be provided to observe per-tensor progress (current/total/name).

Constructors

constructor(sourceProvider: () -> Source, onProgress: (current: Long, total: Long, message: String?) -> Unit = { _, _, _ -> })

open suspend override fun <T : DType, V> load(ctx: ExecutionContext, dtype: KClass<T>, onTensorLoaded: (String, Tensor<T, V>) -> Unit)