Function foldedQuantizedSdpa

foldedQuantizedSdpa(
    q: MlxArray,
    kq: QuantizedTensor,
    vq: QuantizedTensor,
    scale: number,
    groupSize: number,
    bits: number,
): MlxArray
Parameters
- q: MlxArray
- kq: QuantizedTensor
- vq: QuantizedTensor
- scale: number
- groupSize: number
- bits: number
Returns MlxArray
- Defined in packages/inference/src/layers/quantized-attention.ts:145